© 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. 2817
    Prev
    Next
    INDEX
    Explanations

    entity followed by description

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

    section headers and labels

    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
     நீங்கள்
    0.31
    Bạn
    0.29
    <unused557>
    0.29
    ,}
    0.28
    <unused1112>
    0.28
    這樣的
    0.27
    여러분
    0.27
    你就
    0.27
    Voilà
    0.27
    金属
    0.26
    POSITIVE LOGITS
     Name
    0.41
     name
    0.37
    :
    0.37
     starts
    0.36
     started
    0.36
     was
    0.36
    টি
    0.36
     extraordinaire
    0.35
    ing
    0.34
     from
    0.34
    Activations Density 0.379%

    No Known Activations