© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2189
    Prev
    Next
    INDEX
    Explanations

    can be, exist, represent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penile
    0.83
    atschapp
    0.73
    kadot
    0.73
    polyfill
    0.73
    
    0.72
     वाजिब
    0.72
    ܕ
    0.72
     etcétera
    0.71
    <unused1099>
    0.71
    ত্রের
    0.71
    POSITIVE LOGITS
     aucun
    0.67
     handles
    0.66
     likely
    0.63
     handle
    0.63
    場合の
    0.63
     vice
    0.62
    aft
    0.62
     rép
    0.62
    場合
    0.62
     Cmd
    0.62
    Activations Density 0.005%

    No Known Activations