© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 78834
    Prev
    Next
    INDEX
    Explanations

    web hosting, cardiac hypertrophy, whilst

    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
    ßten
    -0.98
     heretofore
    -0.91
    няют
    -0.90
    izoen
    -0.90
     wherein
    -0.88
     "&
    -0.85
    👧
    -0.84
    WithFormat
    -0.83
    ((-
    -0.81
    IZATION
    -0.81
    POSITIVE LOGITS
    Whilst
    0.96
     whilst
    0.96
    glVertex
    0.88
     teenage
    0.86
     named
    0.86
     worded
    0.84
     TOK
    0.83
     risks
    0.82
    riva
    0.82
     debate
    0.80
    Activations Density 0.026%

    No Known Activations