© 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. 223299
    Prev
    Next
    INDEX
    Explanations

    has both

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

    "converse", "see", "wanted", "capturing"

    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
    쐞
    0.52
    нэт
    0.50
    эри
    0.49
    宄
    0.48
    э
    0.48
    ཥ
    0.48
    ಹಾ
    0.47
    ಬ್ಬಿಣ
    0.47
    टॉप
    0.46
     gaping
    0.46
    POSITIVE LOGITS
    0.68
    ina
    0.59
     performances
    0.57
    kt
    0.54
     on
    0.53
    1
    0.53
    com
    0.52
    hy
    0.52
    stv
    0.52
    od
    0.52
    Activations Density 0.000%

    No Known Activations