© 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. 49564
    Prev
    Next
    INDEX
    Explanations

    source from

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

    This neuron fires on occurrences of the token “from,” especially when it appears as a parameter or field name.

    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
     terdekat
    -0.88
     started
    -0.85
    тя
    -0.84
     Kennt
    -0.84
    わた
    -0.84
    会社の
    -0.82
     oddly
    -0.80
    </i>
    -0.78
     pēc
    -0.78
     отеля
    -0.77
    POSITIVE LOGITS
     whom
    1.05
    whom
    1.00
    setFrom
    0.95
     誰
    0.92
    whose
    0.91
    stein
    0.90
    bitField
    0.89
    atting
    0.85
     Whom
    0.84
    olak
    0.81
    Activations Density 0.016%

    No Known Activations