© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    You guessed

    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
    treated
    0.46
    increasing
    0.45
    G
    0.44
    trend
    0.44
    signal
    0.44
     nickname
    0.43
    IS
    0.43
    there
    0.42
    favorite
    0.42
    current
    0.42
    POSITIVE LOGITS
     dürfen
    0.52
     Ressourcen
    0.51
     pourront
    0.50
     konnten
    0.50
     können
    0.49
     Thromb
    0.48
     übrig
    0.48
    䂙
    0.47
     सॉरी
    0.46
     தங்கள்
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.