© 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. 113827
    Prev
    Next
    INDEX
    Explanations

    instructions and sequential words

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

    speech, communication, information

    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
    No
    0.58
     No
    0.50
    Also
    0.50
    also
    0.49
     I
    0.48
    It
    0.48
     also
    0.48
     Also
    0.47
     Joe
    0.47
    fr
    0.46
    POSITIVE LOGITS
     nomenclatura
    0.61
     թվ
    0.59
    кола
    0.57
    缴
    0.57
     структура
    0.55
     ком
    0.55
     үй
    0.54
     企业
    0.54
    كا
    0.53
    㶱
    0.53
    Activations Density 0.000%

    No Known Activations