© 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. 228535
    Prev
    Next
    INDEX
    Explanations

    straight neck

    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
    몰
    0.48
     receiver
    0.47
     juvenile
    0.47
     motivational
    0.45
     ruck
    0.43
    하던
    0.42
     pct
    0.41
     moll
    0.41
     wild
    0.41
    кугӀ
    0.40
    POSITIVE LOGITS
     Вин
    0.52
    ્સ
    0.51
     Đó
    0.51
     Π
    0.49
     περί
    0.49
    сно
    0.49
     clipped
    0.49
    \|_{\
    0.48
    ନ
    0.48
     μα
    0.48
    Activations Density 0.000%

    No Known Activations