© 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. 98211
    Prev
    Next
    INDEX
    Explanations

    upon request or no charge

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

    language and examples

    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
     soigne
    0.43
    HandleTypeDef
    0.40
    SetActive
    0.39
    اا
    0.39
    ㄖ
    0.39
    що
    0.38
     déchir
    0.38
    ческие
    0.38
    ToAction
    0.38
    Ꮥ
    0.38
    POSITIVE LOGITS
    વામાં
    0.49
     replacements
    0.48
     ένα
    0.48
     Moto
    0.48
    ionized
    0.48
     Beverages
    0.46
     Ambient
    0.46
     Ens
    0.45
     Extremely
    0.45
     elemento
    0.44
    Activations Density 0.001%

    No Known Activations