© 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. 79472
    Prev
    Next
    INDEX
    Explanations

    not based, not dependent, not restricted

    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
     não
    -1.34
    ícias
    -1.33
     not
    -1.33
     também
    -1.25
     también
    -1.13
     nesten
    -1.11
     nicht
    -1.05
    chestra
    -1.05
     både
    -1.04
     also
    -1.03
    POSITIVE LOGITS
     directly
    1.66
     always
    1.58
     necessarily
    1.45
     absolutely
    1.35
     completely
    1.25
     strictly
    1.21
     entirely
    1.20
     直接
    1.16
     strict
    1.16
     perfectly
    1.16
    Activations Density 0.142%

    No Known Activations