© 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. 186062
    Prev
    Next
    INDEX
    Explanations

    words followed by descriptors

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

    potential outcomes for entities

    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
     drept
    0.49
     azar
    0.46
    ﹎
    0.45
    জ
    0.45
    সন্ত
    0.44
     siglos
    0.43
    ʺ
    0.42
    ্
    0.42
    '',
    0.42
    nett
    0.42
    POSITIVE LOGITS
     дополнительные
    0.52
     прият
    0.46
    ivin
    0.45
    ergewöhn
    0.44
     дополнительных
    0.44
     प्रोफेशनल
    0.44
     дизайнер
    0.44
    额外的
    0.43
     профе
    0.42
     появля
    0.42
    Activations Density 0.003%

    No Known Activations