© 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. 127641
    Prev
    Next
    INDEX
    Explanations

    measurements and rates of change

    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
     eorum
    -1.10
     activer
    -1.04
    ICIONES
    -1.02
    azer
    -1.02
    Occasionally
    -0.96
    urnya
    -0.94
     attiva
    -0.93
    cend
    -0.92
    cended
    -0.92
    bestos
    -0.92
    POSITIVE LOGITS
     flera
    1.17
     cumulative
    1.06
     several
    1.06
     accumulated
    1.04
     accumulate
    1.02
     מה
    1.02
    iramente
    1.00
     accum
    0.98
    gencias
    0.98
     over
    0.98
    Activations Density 0.040%

    No Known Activations