© 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. 231642
    Prev
    Next
    INDEX
    Explanations

    essay format

    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
    vez
    0.51
    vey
    0.48
     MCI
    0.48
    as
    0.47
    janja
    0.46
     verte
    0.46
    baum
    0.45
     \[
    0.44
     '''
    0.44
    signUp
    0.44
    POSITIVE LOGITS
     radiated
    0.49
    வா
    0.48
    豊かな
    0.46
    அந்த
    0.45
    夏の
    0.45
    печа
    0.44
    眙
    0.44
    ார்கள்
    0.43
    ренные
    0.43
    被害
    0.43
    Activations Density 0.000%

    No Known Activations