© 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. 47045
    Prev
    Next
    INDEX
    Explanations

    out of control

    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
    tecla
    -0.82
    Benefits
    -0.80
     gourmand
    -0.79
    fficient
    -0.75
     necessidade
    -0.75
    žit
    -0.74
    čna
    -0.74
    arlı
    -0.73
     ruines
    -0.72
     tł
    -0.72
    POSITIVE LOGITS
     control
    3.78
    control
    3.19
     Control
    2.86
     controllable
    2.61
    Control
    2.58
     CONTROL
    2.44
     controlar
    2.31
     influence
    2.25
     controls
    2.23
    控制
    2.22
    Activations Density 0.033%

    No Known Activations