© 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. 148874
    Prev
    Next
    INDEX
    Explanations

    off

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

    off-stage, off-course, off-world

    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
     escolas
    0.50
    신도시
    0.49
    리
    0.48
    것
    0.48
    스를
    0.48
    铒
    0.47
    리는
    0.47
    谆
    0.47
    𝚆
    0.47
    诉
    0.46
    POSITIVE LOGITS
    melon
    0.46
    ings
    0.45
    atom
    0.45
    tense
    0.44
    configuration
    0.44
    leader
    0.43
    a
    0.43
    framework
    0.43
    aim
    0.42
    ocean
    0.42
    Activations Density 0.000%

    No Known Activations