© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12248
    Prev
    Next
    INDEX
    Explanations

    introduces summaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ल
    2.08
    Раз
    1.92
    また
    1.72
    रान
    1.69
    От
    1.68
    اشی
    1.68
     فونبټ
    1.68
    Щ
    1.66
    ش
    1.66
     situado
    1.65
    POSITIVE LOGITS
     supply
    1.82
    ‒
    1.80
     stalled
    1.77
     booze
    1.72
     不是
    1.70
    branding
    1.70
     bling
    1.70
    leece
    1.69
    amphetamine
    1.69
     cops
    1.68
    Activations Density 0.265%

    No Known Activations