© 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. 56820
    Prev
    Next
    INDEX
    Explanations

    building blocks of

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

    building blocks

    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
     vicious
    0.44
     clover
    0.43
     रिलेशन
    0.42
    સ
    0.42
    ད
    0.42
    2
    0.42
    ཝ
    0.41
    வி
    0.40
     depressing
    0.40
     dismal
    0.40
    POSITIVE LOGITS
    构成
    0.53
     构建
    0.53
    构建
    0.52
    组成
    0.51
     compone
    0.51
     bricks
    0.51
    ütter
    0.49
     Compose
    0.49
     строи
    0.48
    Undo
    0.48
    Activations Density 0.004%

    No Known Activations