© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4897
    Prev
    Next
    INDEX
    Explanations

    concepts and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixes
    1.97
     strategy
    1.93
     (=
    1.93
     into
    1.92
     của
    1.92
     tactic
    1.90
     procedure
    1.86
     tactics
    1.85
     method
    1.83
     ({\
    1.83
    POSITIVE LOGITS
    6
    2.10
    7
    1.90
    териа
    1.87
    8
    1.84
    чай
    1.83
    торое
    1.82
     fizik
    1.78
     менее
    1.76
    функ
    1.70
    род
    1.68
    Activations Density 0.050%

    No Known Activations