© 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. 175494
    Prev
    Next
    INDEX
    Explanations

    back again assistance

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

    all running processes

    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
    اهای
    0.49
    čenja
    0.47
     دقائق
    0.46
    Subtraction
    0.46
     الخ
    0.46
    gunta
    0.45
     इस्लाम
    0.45
    አ
    0.45
    Instruction
    0.45
     مشکل
    0.44
    POSITIVE LOGITS
    }-(\
    0.44
    ស្រ
    0.44
     give
    0.42
     intentions
    0.42
     Figma
    0.42
     establish
    0.41
    ందించ
    0.41
    <0xB9>
    0.41
    谐
    0.41
    互相
    0.40
    Activations Density 0.001%

    No Known Activations