© 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. 164218
    Prev
    Next
    INDEX
    Explanations

    type of descriptive phrases

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

    Literal meaning, specific topics

    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
    a
    0.56
    r
    0.52
    lar
    0.46
    is
    0.46
    in
    0.45
    h
    0.45
    some
    0.45
    </h2>
    0.44
    sha
    0.44
    बरी
    0.43
    POSITIVE LOGITS
     lähe
    0.56
     pensioners
    0.54
     chirop
    0.51
     brigades
    0.51
    ahlen
    0.49
     رجال
    0.49
     അനു
    0.48
     complète
    0.48
     純
    0.48
    <unused2124>
    0.48
    Activations Density 0.001%

    No Known Activations