© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2669
    Prev
    Next
    INDEX
    Explanations

    framing and portrayal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     및
    0.92
    .",
    0.92
    ).
    0.89
    为止
    0.87
    !.
    0.79
     forskjellige
    0.78
     گا۔
    0.78
     کیا۔
    0.77
     عنه
    0.76
    !).
    0.76
    POSITIVE LOGITS
    خواندن
    0.80
    phas
    0.79
    حم
    0.77
     abst
    0.75
    RuntimeException
    0.75
     reuniones
    0.74
    ળો
    0.73
    之为
    0.73
     acciones
    0.72
    ょ
    0.71
    Activations Density 0.268%

    No Known Activations