© 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. 81759
    Prev
    Next
    INDEX
    Explanations

    specific vehicle types

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

    get away

    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
    Negative Logits
    s
    0.49
     creative
    0.48
    L
    0.48
    NO
    0.46
     in
    0.45
     personal
    0.45
     hostile
    0.44
    싫
    0.43
     vog
    0.42
    organe
    0.42
    POSITIVE LOGITS
     صحی
    0.52
    𒌅
    0.50
     QnrB
    0.49
     යු
    0.48
     tetapi
    0.48
     DCHECK
    0.47
    टाइ
    0.47
     لیکن
    0.47
     astrophysics
    0.46
     ancak
    0.46
    Activations Density 0.001%

    No Known Activations