© 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. 205
    Prev
    Next
    INDEX
    Explanations

    by [proper noun or descriptive word]

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

    creator or author attribution

    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
     నొప్పి
    0.32
     Retour
    0.32
     விழுப்பு
    0.29
     vraie
    0.29
    റുണ്ട്
    0.29
     بده
    0.29
     fname
    0.28
    亏
    0.28
     Datenschutz
    0.28
     свадь
    0.28
    POSITIVE LOGITS
     oleh
    0.49
     Andrew
    0.48
     proponents
    0.48
     by
    0.48
     Robert
    0.47
     experts
    0.46
     David
    0.45
     scientists
    0.45
     astronomers
    0.45
     researchers
    0.45
    Activations Density 0.210%

    No Known Activations