© 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. 59203
    Prev
    Next
    INDEX
    Explanations

    anon #, anon (

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

    performance and scores

    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
    垷
    0.51
    GALAD
    0.50
    鿓
    0.50
    㴡
    0.49
    靛
    0.48
     партії
    0.48
    假期
    0.47
    激励
    0.47
    ٹے
    0.47
    憉
    0.46
    POSITIVE LOGITS
     (
    0.61
    1
    0.51
     Power
    0.50
     or
    0.48
     and
    0.46
    (),
    0.46
    3
    0.46
     on
    0.44
     Guru
    0.44
     ([]
    0.44
    Activations Density 0.000%

    No Known Activations