© 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. 47589
    Prev
    Next
    INDEX
    Explanations

    speaks for itself

    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
    ifed
    -0.88
     advice
    -0.87
    specifically
    -0.86
     cinco
    -0.86
     À
    -0.85
    lieved
    -0.84
     dobre
    -0.84
     acht
    -0.84
     exceptionally
    -0.83
    irah
    -0.82
    POSITIVE LOGITS
     volumes
    2.55
     Volumes
    1.70
    volumes
    1.59
     volume
    1.58
    volume
    1.55
    Volumes
    1.50
     loudly
    1.27
    Volume
    1.23
     itself
    1.20
     louder
    1.19
    Activations Density 0.020%

    No Known Activations