© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 251724
    Prev
    Next
    INDEX
    Explanations

    external services or locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     கட்டிட
    0.46
    堵
    0.45
    ்சை
    0.43
     characteristic
    0.42
    上半
    0.42
    集体
    0.42
     Tổ
    0.41
    াঃ
    0.41
    ：“
    0.41
     grados
    0.41
    POSITIVE LOGITS
    maz
    0.46
    mera
    0.46
    ;?>
    0.46
    amera
    0.45
    l
    0.45
    nection
    0.45
     affirm
    0.45
    odal
    0.44
    isim
    0.44
     mez
    0.44
    Activations Density 0.002%

    No Known Activations