© 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. 133691
    Prev
    Next
    INDEX
    Explanations

    year regarding

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

    access blocked websites

    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
    in
    0.52
    وة
    0.50
     persönliche
    0.46
    inį
    0.45
    <0x80>
    0.45
    书中
    0.45
    development
    0.43
    槎
    0.43
     öt
    0.43
    itä
    0.42
    POSITIVE LOGITS
     aldehyde
    0.54
     predicated
    0.48
     aldehydes
    0.47
     drawstring
    0.47
     analogs
    0.46
     চোপ
    0.46
    クセ
    0.45
     asympt
    0.44
     oxidation
    0.43
    也會
    0.43
    Activations Density 0.001%

    No Known Activations