© 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. 173735
    Prev
    Next
    INDEX
    Explanations

    colors, adjectives, and niche terms

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

    validates a market

    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
    י
    0.50
     apocalyptic
    0.48
     scarcely
    0.47
     historian
    0.43
     divergent
    0.43
    py
    0.42
     cod
    0.42
     hardly
    0.42
     typology
    0.42
     walled
    0.41
    POSITIVE LOGITS
     blanchâtre
    0.55
     thisobject
    0.53
     لون
    0.51
     considérer
    0.50
    浸
    0.49
     způ
    0.48
     luisant
    0.47
    endroit
    0.47
    ベージュ
    0.47
     झांसी
    0.46
    Activations Density 0.000%

    No Known Activations