© 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. 76335
    Prev
    Next
    INDEX
    Explanations

    recipient, recipients

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

    constructor parameters and database column names

    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
    𝙽
    0.46
     desaparecer
    0.44
    arlene
    0.43
    getDocument
    0.41
     desapare
    0.41
    arq
    0.41
    kaç
    0.39
    $\\
    0.39
    लामा
    0.39
    𝚈
    0.39
    POSITIVE LOGITS
     recipient
    0.41
    []{
    0.40
    点が
    0.40
     pendant
    0.40
     land
    0.39
     відповід
    0.38
     quali
    0.37
    Recipient
    0.37
     recipients
    0.37
     éprou
    0.36
    Activations Density 0.001%

    No Known Activations