© 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. 77657
    Prev
    Next
    INDEX
    Explanations

    so followed by action

    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
    ždý
    -1.05
    rmdir
    -1.02
    ίναι
    -1.02
     pérd
    -1.00
    ERÍA
    -0.98
    chandise
    -0.98
    Чита
    -0.97
    rogène
    -0.96
    واس
    -0.94
    jednoc
    -0.94
    POSITIVE LOGITS
     off
    4.34
    Off
    2.47
     into
    2.42
    off
    2.39
     Off
    2.30
     away
    2.27
     onto
    2.16
     OFF
    1.94
     down
    1.81
     out
    1.73
    Activations Density 0.037%

    No Known Activations