© 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. 139586
    Prev
    Next
    INDEX
    Explanations

    patterns in text lists

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

    multilingual concepts and social issues

    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
    handlung
    0.43
    １
    0.42
     时
    0.40
    seller
    0.39
     Seller
    0.39
     Chancery
    0.38
    笔
    0.38
     Decade
    0.38
    ２
    0.38
    აბ
    0.38
    POSITIVE LOGITS
     insanların
    0.48
     bairro
    0.48
     अक्सर
    0.47
    民眾
    0.46
    ̓
    0.46
     pungent
    0.46
     porous
    0.45
     penerapan
    0.44
    }=$
    0.44
     peculi
    0.44
    Activations Density 0.000%

    No Known Activations