© 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. 165563
    Prev
    Next
    INDEX
    Explanations

    events and research

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

    requires attention

    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
    انيه
    0.48
     bý
    0.48
    ابي
    0.48
    كينا
    0.46
    toEqual
    0.46
    𝗄
    0.44
    clients
    0.44
    ن
    0.44
    如果您
    0.43
    افي
    0.43
    POSITIVE LOGITS
    oS
    0.50
    orschung
    0.47
    Ｘ
    0.47
    indexing
    0.46
    oque
    0.45
     चमक
    0.45
    strain
    0.45
    sentation
    0.45
     바람
    0.45
    orschungs
    0.45
    Activations Density 0.001%

    No Known Activations