© 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. 168299
    Prev
    Next
    INDEX
    Explanations

    handling heat

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

    eyes holding the color

    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
    ｲ
    0.55
    ၻ
    0.50
     Jax
    0.46
     karna
    0.45
     panther
    0.45
     панели
    0.45
    ｿ
    0.45
    が多い
    0.45
    ﾆ
    0.45
     இணைந்து
    0.44
    POSITIVE LOGITS
     by
    0.50
     for
    0.44
    ieht
    0.44
    čen
    0.42
    from
    0.41
    prud
    0.41
    by
    0.41
     minist
    0.40
    ều
    0.40
    ció
    0.40
    Activations Density 0.000%

    No Known Activations