© 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. 182265
    Prev
    Next
    INDEX
    Explanations

    value display

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

    closing your eyes

    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
     ovary
    0.50
    琯
    0.46
     sätt
    0.46
     așa
    0.45
    ྔ
    0.45
     مقارنه
    0.44
    埤
    0.44
     ఆరోగ్య
    0.43
     anormal
    0.43
     ഉരു
    0.43
    POSITIVE LOGITS
    B
    0.60
    OCS
    0.52
    ing
    0.48
    𝗕
    0.47
    P
    0.47
    goes
    0.46
     finalised
    0.46
     Critic
    0.46
    Y
    0.46
    C
    0.45
    Activations Density 0.000%

    No Known Activations