© 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. 57547
    Prev
    Next
    INDEX
    Explanations

    her parents

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

    good afternoon / good evening

    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
     de
    0.48
    约束
    0.48
     ge
    0.46
    涛
    0.45
    rimer
    0.44
     compos
    0.44
     znacznie
    0.43
     ikke
    0.43
    нка
    0.43
     product
    0.43
    POSITIVE LOGITS
    CHICAGO
    0.51
     juries
    0.47
     nightclubs
    0.46
    regardless
    0.46
     امریکہ
    0.45
    ₫
    0.45
    DEN
    0.45
    बॉलीवुड
    0.44
     jurors
    0.44
     نوفمبر
    0.44
    Activations Density 0.000%

    No Known Activations