© 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. 193804
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    awkwardness and potential topics

    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
     Indications
    0.53
     Gender
    0.52
     Attorney
    0.50
     KENT
    0.49
     assigned
    0.49
    控
    0.48
     CREAM
    0.47
     Tenants
    0.46
     Controlled
    0.45
    1
    0.45
    POSITIVE LOGITS
    lüğü
    0.48
     ক্রিকে
    0.48
    ல்கள்
    0.48
     jeu
    0.46
    amse
    0.46
    ặp
    0.45
     işle
    0.45
     bể
    0.45
     ló
    0.45
    inom
    0.44
    Activations Density 0.001%

    No Known Activations