© 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. 177183
    Prev
    Next
    INDEX
    Explanations

    great idea, up to, coming to

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

    English primary language

    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
    ुलम
    0.47
     भेजा
    0.46
     understated
    0.46
    बंधनाच्या
    0.45
     ആഘോഷ
    0.45
     ፍ
    0.45
    ارهای
    0.44
    करण
    0.43
    ंबा
    0.43
    нци
    0.43
    POSITIVE LOGITS
    的设计
    0.48
    後
    0.46
    eas
    0.45
    U
    0.44
    t
    0.44
    р
    0.44
    Designs
    0.44
    བྱ
    0.43
    Design
    0.43
    at
    0.42
    Activations Density 0.000%

    No Known Activations