© 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. 235772
    Prev
    Next
    INDEX
    Explanations

    black sport loop, black lentils, old harbour

    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
    謢
    0.44
     demolished
    0.43
    冼
    0.43
    勖
    0.43
    损坏
    0.42
    lamydia
    0.42
    示范
    0.42
    竭
    0.42
    ቻ
    0.41
     turner
    0.41
    POSITIVE LOGITS
    ROOM
    0.51
     IS
    0.50
     ご
    0.50
    )~
    0.49
     子供
    0.48
    )
    0.48
    LS
    0.47
    seller
    0.45
    color
    0.44
    ROW
    0.44
    Activations Density 0.000%

    No Known Activations