© 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. 236524
    Prev
    Next
    INDEX
    Explanations

    Names and specific 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
     deaktiv
    0.56
     پڑ
    0.55
    禪
    0.54
    گوید
    0.54
    phobic
    0.52
    inscription
    0.52
     terce
    0.50
     demandé
    0.50
    ranking
    0.50
    顰
    0.50
    POSITIVE LOGITS
     Vickers
    0.49
     Holden
    0.48
     Clayton
    0.46
     Rockwell
    0.45
     Hager
    0.44
     Frankfort
    0.44
     Harlow
    0.43
     Leighton
    0.43
     Dickinson
    0.42
     Hastings
    0.42
    Activations Density 0.002%

    No Known Activations