© 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. 239077
    Prev
    Next
    INDEX
    Explanations

    start of sentence or clause

    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
    vané
    0.46
     oficiais
    0.45
    ن
    0.43
     الرسم
    0.43
    有哪些
    0.42
    CAG
    0.41
     sweetened
    0.41
    흡
    0.41
    Compiled
    0.40
    പ്പിച്ച്
    0.40
    POSITIVE LOGITS
     Knoxville
    0.48
    lm
    0.47
     Länder
    0.47
     femoral
    0.46
    譏
    0.46
    𝟘
    0.46
     Euclidean
    0.45
     Kosovo
    0.44
     sdf
    0.44
     slime
    0.43
    Activations Density 0.000%

    No Known Activations