© 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. 174930
    Prev
    Next
    INDEX
    Explanations

    Daily Method of Operation

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

    British Inspector Crown

    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
    ability
    0.51
     orientación
    0.51
     curvatures
    0.50
    ج
    0.49
    (~
    0.48
     opération
    0.48
     operación
    0.47
     ediyoruz
    0.46
     perpend
    0.46
     effettuare
    0.45
    POSITIVE LOGITS
     ポ
    0.46
     British
    0.46
    kish
    0.45
     monk
    0.44
     Dorian
    0.44
    ↵
    0.43
     Inspector
    0.43
     Britain
    0.43
     RU
    0.43
     Twelve
    0.43
    Activations Density 0.001%

    No Known Activations