© 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. 18629
    Prev
    Next
    INDEX
    Explanations

    largely requested, quite refreshing, very common

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

    creating or used as

    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
     C
    0.44
    guard
    0.42
    Marker
    0.42
    Rt
    0.42
     condensed
    0.41
     sprinkling
    0.40
    watch
    0.40
    Watts
    0.40
     sprinkled
    0.40
     racially
    0.40
    POSITIVE LOGITS
     জুটি
    0.49
    🤢
    0.48
    aloko
    0.46
    ITERATURE
    0.46
    🚣
    0.45
    UTONIUM
    0.45
    ังสือ
    0.45
    👎
    0.45
     Animations
    0.45
    𝔦
    0.45
    Activations Density 0.000%

    No Known Activations