© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5853
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     انه
    1.82
     potrebbero
    1.74
    これらの
    1.73
    也都
    1.73
    也将
    1.70
    ']):
    1.67
    ?!"
    1.66
     недавно
    1.65
    ?".
    1.64
    eea
    1.64
    POSITIVE LOGITS
     vs
    2.24
     versus
    2.12
    ->
    1.90
    versus
    1.84
     ->
    1.76
     +
    1.71
    →
    1.65
     /
    1.64
     >
    1.58
    first
    1.56
    Activations Density 0.195%

    No Known Activations