© 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. 32889
    Prev
    Next
    INDEX
    Explanations

    prést,ඕ, रांची, govor, beton

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

    sermon or speech writing

    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
     صفحۀ
    0.46
    द्रा
    0.43
    Result
    0.41
     dancers
    0.40
    currentPage
    0.40
    🫧
    0.39
     Attorneys
    0.39
    =?";
    0.39
    🥰
    0.39
     discussions
    0.39
    POSITIVE LOGITS
     bloke
    0.55
    OCK
    0.44
    崛
    0.44
     prést
    0.44
     ඕ
    0.43
     रांची
    0.43
     govor
    0.42
     beton
    0.42
     olma
    0.42
     рабочей
    0.42
    Activations Density 0.020%

    No Known Activations