© 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. 87799
    Prev
    Next
    INDEX
    Explanations

    Petty aircraft armour West Side

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

    autocomplete on your phone

    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
     Provides
    0.52
     Helps
    0.52
     Gives
    0.48
     Refs
    0.48
     অতঃ
    0.48
     lily
    0.47
    '></
    0.46
     Fish
    0.46
     Remove
    0.45
     Cheat
    0.45
    POSITIVE LOGITS
    Bachelor
    0.50
    нется
    0.46
    ни
    0.46
    нее
    0.46
    larında
    0.46
     yerine
    0.45
    가
    0.45
    Sebastian
    0.45
    der
    0.45
    thousand
    0.44
    Activations Density 0.001%

    No Known Activations