© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 94230
    Prev
    Next
    INDEX
    Explanations

    Angular component selector

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    紧张
    -0.82
    にの
    -0.80
    మ్
    -0.77
     coldly
    -0.77
    Köszönöm
    -0.76
    ʏ
    -0.76
     amitié
    -0.75
     offended
    -0.75
     benne
    -0.74
    йом
    -0.72
    POSITIVE LOGITS
     template
    1.12
    selector
    1.04
    template
    1.00
     inputs
    0.99
     styles
    0.99
     selector
    0.98
    templateUrl
    0.98
     host
    0.93
     templates
    0.93
    𝕜
    0.85
    Activations Density 0.021%

    No Known Activations