© 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. 158944
    Prev
    Next
    INDEX
    Explanations

    dull compared to

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

    struck both

    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
    ，
    0.49
    ì
    0.49
    X
    0.49
    le
    0.49
    =
    0.48
    ?
    0.48
    ce
    0.48
    ↵↵
    0.47
    _
    0.47
    \
    0.47
    POSITIVE LOGITS
     imprescindible
    0.56
    ండోత్సర్గము
    0.56
     עי
    0.55
     objectifs
    0.53
    榃
    0.53
    墘
    0.52
     ανάπτυ
    0.52
     اولین
    0.51
     etapa
    0.50
     Fonction
    0.50
    Activations Density 0.000%

    No Known Activations