© 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. 145608
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    в
    0.37
    venida
    0.36
     турни
    0.36
    ԁ
    0.34
     في
    0.34
     沒有
    0.34
     ವರ್ಷ
    0.33
    ꔹ
    0.33
     или
    0.33
     ۔
    0.33
    POSITIVE LOGITS
     dyes
    0.32
     ep
    0.31
     pathos
    0.31
     elektro
    0.30
     elektrom
    0.30
     Diels
    0.30
     thermo
    0.30
     Herstellung
    0.30
     materia
    0.30
     metamorph
    0.30
    Activations Density 0.000%

    No Known Activations