© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13449
    Prev
    Next
    INDEX
    Explanations

    foreign language introductions

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

    knowledge cutoff

    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
    पुरी
    0.45
    JOHN
    0.44
    ট্র
    0.42
    磁
    0.42
     piazza
    0.41
    Directory
    0.41
    ίν
    0.41
    LAST
    0.41
    Convention
    0.40
    ци
    0.39
    POSITIVE LOGITS
    ២
    0.51
     calmed
    0.50
     geschaffen
    0.49
     آزمایش
    0.49
    ലെസ്
    0.49
     Elemente
    0.48
     اسرائیل
    0.48
     logique
    0.48
     entstanden
    0.48
    NotBlank
    0.48
    Activations Density 0.000%

    No Known Activations