© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86884
    Prev
    Next
    INDEX
    Explanations

    groups, audiences, things

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

    feels like

    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
     ย
    0.48
     apunt
    0.47
    yad
    0.47
    Keys
    0.46
    cad
    0.46
    cua
    0.46
     Keys
    0.45
     ",
    0.44
    >",
    0.43
    yh
    0.43
    POSITIVE LOGITS
     पोस्ट
    0.46
    гів
    0.45
     জিয়া
    0.44
    化
    0.43
    距离
    0.43
    电阻
    0.42
     infections
    0.42
    說
    0.42
    Remove
    0.42
    ρν
    0.41
    Activations Density 0.000%

    No Known Activations