© 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. 91005
    Prev
    Next
    INDEX
    Explanations

    preceding technical terms

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

    types of costs or nouns

    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
    .​
    0.45
     resulta
    0.43
     ignited
    0.43
     Rival
    0.42
     لما
    0.41
     computes
    0.41
     inventories
    0.41
     nisso
    0.41
     isso
    0.40
    ​.
    0.40
    POSITIVE LOGITS
     COT
    0.53
     第一
    0.52
     GOVERNMENT
    0.50
     HIST
    0.50
     GAMES
    0.48
    ータ
    0.48
    STY
    0.47
    ränkt
    0.46
    ük
    0.46
     STEP
    0.46
    Activations Density 0.000%

    No Known Activations