© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31313
    Prev
    Next
    INDEX
    Explanations

    positive and negative classifications

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ₁(
    -0.91
    glPopMatrix
    -0.85
     fragt
    -0.79
    cnica
    -0.78
     bewegt
    -0.76
    amazonaws
    -0.75
     elegance
    -0.74
     devastation
    -0.74
    iesen
    -0.74
     honoured
    -0.74
    POSITIVE LOGITS
     outweigh
    1.11
     experiences
    1.08
     towards
    1.01
     (+)
    0.96
     feedback
    0.95
     toward
    0.94
     experiencias
    0.93
    CROSSTALK
    0.92
     Negative
    0.92
     reviews
    0.88
    Activations Density 0.045%

    No Known Activations