© 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. 141412
    Prev
    Next
    INDEX
    Explanations

    phrases following common words

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

    European sun

    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
    Negative Logits
     team
    0.52
    팀
    0.47
     équipe
    0.44
     kra
    0.42
    team
    0.41
     censure
    0.41
     inaugural
    0.41
     cabinet
    0.41
     eleven
    0.41
     Cabinet
    0.40
    POSITIVE LOGITS
    Temporal
    0.51
    sqrt
    0.47
    NAVIGATION
    0.47
    UNRELATED
    0.46
    碳
    0.46
    燔
    0.46
    STATUS
    0.45
     товары
    0.45
     अराउंड
    0.45
    )^{-
    0.45
    Activations Density 0.001%

    No Known Activations