© 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. 94510
    Prev
    Next
    INDEX
    Explanations

    Rt / Housing / Hermione / Compiled

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

    CPU ID, tradition, birth date

    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
    評
    0.46
    ველ
    0.43
    適用
    0.41
    ック
    0.41
    ässer
    0.41
    勾
    0.40
    门口
    0.40
    쫒
    0.40
    གས་
    0.40
    시
    0.40
    POSITIVE LOGITS
     infe
    0.53
    tant
    0.53
    tamb
    0.52
    tw
    0.50
     рели
    0.48
    tans
    0.48
    ting
    0.47
    typen
    0.47
    ke
    0.47
    dle
    0.47
    Activations Density 0.000%

    No Known Activations