© 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. 22-GEMMASCOPE-RES-131K
    7. 64305
    Prev
    Next
    INDEX
    Explanations

    estimating LR approach

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     kokona
    -1.10
     puissiez
    -1.00
    Visitation
    -0.98
     our
    -0.96
     افزود
    -0.95
    Vorlage
    -0.93
     учет
    -0.92
    бочки
    -0.90
     dormitórios
    -0.88
    گردان
    -0.88
    POSITIVE LOGITS
    almacen
    0.95
     coussin
    0.93
    🟠
    0.91
    らす
    0.90
    átor
    0.90
     cq
    0.90
     explications
    0.90
     hoes
    0.90
     NSM
    0.88
     JES
    0.88
    Activations Density 0.073%

    No Known Activations