© 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. 3134
    Prev
    Next
    INDEX
    Explanations

    date and number separators

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

    numbers, slashes, or operating systems

    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
     гульнявыя
    0.40
     ধর্ষণ
    0.38
    <unused88>
    0.38
    <unused57>
    0.38
    瘍
    0.38
    🕓
    0.37
    <unused51>
    0.37
     вопроса
    0.37
    ᒐ
    0.37
    <unused2136>
    0.36
    POSITIVE LOGITS
    h
    0.72
    the
    0.70
    ur
    0.64
    ↵↵
    0.62
    per
    0.61
    to
    0.60
    /
    0.60
    w
    0.58
    ch
    0.57
    u
    0.57
    Activations Density 0.167%

    No Known Activations