© 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. 159558
    Prev
    Next
    INDEX
    Explanations

    storage and conditions

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

    | band, data, errors, shopping

    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
    িকা
    0.46
    ্ড
    0.46
    াসা
    0.44
     及
    0.43
    вае
    0.43
     saranam
    0.42
    佺
    0.42
    ܝܢ
    0.42
     জুড়ে
    0.42
    していました
    0.42
    POSITIVE LOGITS
     concealed
    0.48
     expedited
    0.46
     stipulations
    0.46
    fass
    0.46
     stipulation
    0.46
    verk
    0.45
     stipulated
    0.45
     meager
    0.45
     ignorance
    0.44
     angesehen
    0.44
    Activations Density 0.001%

    No Known Activations