© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    html attributes

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

    html attribute assignments

    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
     intestines
    0.34
    <unused69>
    0.33
    郯
    0.32
    <unused24>
    0.32
    <unused74>
    0.32
    禟
    0.31
     kanamycin
    0.30
    ফটেন্যান্ট
    0.30
     রোগে
    0.30
    <unused9>
    0.30
    POSITIVE LOGITS
    info
    0.40
    content
    0.40
    id
    0.39
    text
    0.39
    it
    0.38
    ↵↵
    0.38
    set
    0.38
    if
    0.37
    s
    0.37
    ве
    0.37
    Activations Density 0.005%

    No Known Activations