© 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. 84501
    Prev
    Next
    INDEX
    Explanations

    stocking

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

    converting or combining parts

    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
     تے
    0.47
    ляє
    0.47
     }:
    0.46
    ݨ
    0.45
    નમાં
    0.44
    __:
    0.43
    ïde
    0.41
    쾨
    0.41
    ወቅ
    0.41
    ྛ
    0.41
    POSITIVE LOGITS
     Tara
    0.49
     that
    0.48
     kaos
    0.47
     Xs
    0.47
     GPS
    0.47
     ludzi
    0.47
     of
    0.46
     Mes
    0.45
     it
    0.45
     crew
    0.45
    Activations Density 0.000%

    No Known Activations