© 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. 6499
    Prev
    Next
    INDEX
    Explanations

    evidence and responsibility

    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
     Howell
    2.03
    ність
    2.03
     Chips
    2.02
    нії
    2.00
    intahan
    1.99
    ń
    1.98
     Ruiz
    1.96
    ності
    1.96
     Machado
    1.94
     Ávila
    1.93
    POSITIVE LOGITS
    eth
    0.75
    ELSE
    0.64
    AST
    0.58
    St
    0.58
    Sto
    0.58
    –
    0.57
    IND
    0.57
    ETH
    0.56
    Congressional
    0.53
    K
    0.52
    Activations Density 0.028%

    No Known Activations