© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77382
    Prev
    Next
    INDEX
    Explanations

    Edmund Burke hospital mortality

    np_acts-logits-general · gemini-2.5-flash-lite

    proper names and terms associated with entrances, exits, and locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words and tokens that denote entry or opening (e.g. entrance, admission/opening).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visse
    -0.80
     Edelstahl
    -0.76
    ον
    -0.73
     tesoro
    -0.72
    inf
    -0.71
     infrequently
    -0.71
    Поэтому
    -0.71
    gm
    -0.70
     App
    -0.69
    AT
    -0.68
    POSITIVE LOGITS
    welle
    0.85
     Ingo
    0.84
    <0xA8>
    0.82
    σία
    0.81
     hospital
    0.81
     settlers
    0.79
    parken
    0.79
    hatenablog
    0.78
    ipedi
    0.76
    stånd
    0.76
    Activations Density 0.005%

    No Known Activations