© 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. 1345
    Prev
    Next
    INDEX
    Explanations

    unpublished dispositions

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

    The neuron strongly activates on numeric tokens (e.g. multi‐digit numbers such as years, rule numbers, IDs, etc.).

    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
     Navidad
    -0.75
    сете
    -0.67
     Regardless
    -0.66
    |]
    -0.65
    chute
    -0.65
     ground
    -0.65
     allowing
    -0.65
     ネックレス
    -0.65
    etna
    -0.63
     }^{*}
    -0.63
    POSITIVE LOGITS
    Petro
    0.77
    negoti
    0.77
    krank
    0.76
     realist
    0.74
     Continue
    0.73
     MEANS
    0.73
     spécifique
    0.71
    Continue
    0.71
    cabul
    0.70
    Jen
    0.70
    Activations Density 0.033%

    No Known Activations