© 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. 169754
    Prev
    Next
    INDEX
    Explanations

    costs and fees

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

    multilingual relation contexts

    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
    itories
    0.47
    教師
    0.47
    UIServer
    0.46
    omeres
    0.46
     lentils
    0.45
    ιών
    0.44
     columnar
    0.44
    鱉
    0.43
     prisms
    0.43
     ritor
    0.43
    POSITIVE LOGITS
     a
    0.46
     paramètres
    0.45
     EXCHANGE
    0.43
     میان
    0.42
     अनुया
    0.42
    贞
    0.41
    队的
    0.41
     denote
    0.41
     discourage
    0.41
     Ген
    0.40
    Activations Density 0.001%

    No Known Activations