© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1182
    Prev
    Next
    INDEX
    Explanations

    guides and blank

    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
     PID
    -0.88
    Pid
    -0.80
     useState
    -0.79
     pila
    -0.77
     Stere
    -0.76
    PID
    -0.75
     Remembrance
    -0.75
    Funcionario
    -0.73
    Frauen
    -0.68
    髏
    -0.68
    POSITIVE LOGITS
     guides
    1.27
     Guides
    1.13
     blanks
    1.10
     guide
    1.09
     blank
    1.05
    Guides
    1.00
    ガイド
    1.00
     tip
    0.96
    guides
    0.95
     Blank
    0.92
    Activations Density 0.006%

    No Known Activations