© 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. 54622
    Prev
    Next
    INDEX
    Explanations

    goods and services

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

    puns and wordplay

    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
    nivel
    0.49
    ();
    0.47
     удоволь
    0.45
    el
    0.45
    ፡
    0.45
    TorpedoStore
    0.45
    $
    0.45
    transaction
    0.44
    §
    0.43
    al
    0.43
    POSITIVE LOGITS
     pob
    0.48
     sini
    0.45
     roofing
    0.45
     leopards
    0.45
     rooftops
    0.44
     lengths
    0.44
     Jessie
    0.44
     glauben
    0.43
     premises
    0.43
    гово
    0.43
    Activations Density 0.000%

    No Known Activations