© 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. 123044
    Prev
    Next
    INDEX
    Explanations

    purpose beyond survival

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

    sugar-free / zero sugar options

    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
     artistes
    0.49
     artiste
    0.47
    アーティスト
    0.47
     artistas
    0.46
     આ
    0.44
     Artists
    0.42
     indústria
    0.42
     televiz
    0.42
     artisti
    0.42
     esclusivamente
    0.42
    POSITIVE LOGITS
     सेफ्टी
    0.46
    嘣
    0.46
    сим
    0.44
    жене
    0.44
     regaining
    0.43
    íta
    0.42
    kert
    0.42
    irtual
    0.42
    ቱም
    0.42
    siege
    0.42
    Activations Density 0.000%

    No Known Activations