© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31569
    Prev
    Next
    INDEX
    Explanations

    foreign or niche words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    from
    0.54
     incumbents
    0.47
     elevators
    0.47
     entail
    0.45
     from
    0.44
     decar
    0.44
     effort
    0.43
    .
    0.43
     revealing
    0.43
     lantern
    0.42
    POSITIVE LOGITS
     アイス
    0.54
     आइकॉन
    0.53
     ഭക്ഷണ
    0.52
     Maked
    0.52
    odni
    0.51
    geoType
    0.51
     Ferien
    0.49
     Fears
    0.49
     वॉटर
    0.49
    <unused2183>
    0.48
    Activations Density 0.005%

    No Known Activations