© 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. 27083
    Prev
    Next
    INDEX
    Explanations

    not only

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

    entity definition

    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
    сная
    0.46
    𒌍
    0.45
    様々な
    0.44
    ியான
    0.44
    Syair
    0.43
    сона
    0.43
     जता
    0.42
    した
    0.42
    ная
    0.41
    |,
    0.41
    POSITIVE LOGITS
    prar
    0.54
     olefins
    0.47
    actifs
    0.45
     espèces
    0.45
     megs
    0.45
     clínicos
    0.44
     kommen
    0.44
     leite
    0.44
     wären
    0.44
     bakteri
    0.44
    Activations Density 0.000%

    No Known Activations