© 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. 15058
    Prev
    Next
    INDEX
    Explanations

    over a duration

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

    over time

    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
     THREE
    0.46
     nasal
    0.46
     BLOOD
    0.46
     Hunting
    0.45
     RELATION
    0.44
     FIVE
    0.43
     STAY
    0.43
    凪
    0.42
     pant
    0.41
    PLICATIONS
    0.41
    POSITIVE LOGITS
    !),
    0.53
    cccc
    0.48
    bgcolor
    0.46
     сюда
    0.45
    ⅼ
    0.44
    mx
    0.43
    ęcie
    0.42
     perfettamente
    0.42
    ре
    0.42
    यहां
    0.41
    Activations Density 0.000%

    No Known Activations