© 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. 46211
    Prev
    Next
    INDEX
    Explanations

    https://

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

    text, file, CSV encodings

    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
    conjug
    0.43
     conjugates
    0.42
    غام
    0.41
     conjugate
    0.39
    akit
    0.39
     unglaublich
    0.38
    윕
    0.38
     fugit
    0.38
     riches
    0.37
     Göl
    0.36
    POSITIVE LOGITS
     আলা
    0.47
     درجہ
    0.47
     कामका
    0.44
    口感
    0.44
     冷
    0.42
     fecha
    0.41
     गीत
    0.41
     NSUTF
    0.41
    asctime
    0.41
     यूरोपीय
    0.40
    Activations Density 0.000%

    No Known Activations