© 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. 248614
    Prev
    Next
    INDEX
    Explanations

    words following `pull`, `Purchaser`, `grout`, `background`, `primer`

    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
    /
    0.51
    //
    0.48
     Bourgoin
    0.46
    એ
    0.46
    .
    0.45
     навча
    0.43
    見える
    0.41
     учеб
    0.41
     Declined
    0.40
    -
    0.40
    POSITIVE LOGITS
    excess
    0.49
    isComposite
    0.49
    矽
    0.48
    highly
    0.48
    approximately
    0.47
    regions
    0.47
    EVEN
    0.47
    メント
    0.46
    important
    0.46
    aktur
    0.46
    Activations Density 0.001%

    No Known Activations