© 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. 132492
    Prev
    Next
    INDEX
    Explanations

    SPECIAL ISSUE, health Literacy, million views, Your kids

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

    personal contacts and tasks

    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
     квартиры
    0.49
    in
    0.47
    cities
    0.46
     infar
    0.46
     basement
    0.44
    ם
    0.44
    ant
    0.42
    horses
    0.42
    ও
    0.42
    artifact
    0.41
    POSITIVE LOGITS
     ชื่อ
    0.49
     پنج
    0.48
     Dön
    0.48
     Ricardo
    0.47
     MotoGP
    0.46
     چهار
    0.45
     Desire
    0.45
     Wider
    0.45
     Yıld
    0.45
     Sense
    0.45
    Activations Density 0.001%

    No Known Activations