© 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. 89398
    Prev
    Next
    INDEX
    Explanations

    register interest

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

    anti-racist resources

    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
     přes
    0.49
     novela
    0.47
    気
    0.44
     congested
    0.43
    क्सर
    0.43
    气的
    0.42
    懊
    0.41
     અથ
    0.41
     Bonif
    0.40
     Retriever
    0.40
    POSITIVE LOGITS
    cü
    0.46
    DA
    0.46
    ียม
    0.46
    েজ
    0.45
    oyens
    0.45
    hammad
    0.45
    रन
    0.45
    なかった
    0.44
    sensing
    0.43
    ꜱ
    0.43
    Activations Density 0.001%

    No Known Activations