© 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. 78653
    Prev
    Next
    INDEX
    Explanations

    making or to make something

    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
    хол
    -0.85
    瓒
    -0.79
    GGI
    -0.78
    aian
    -0.75
    wasi
    -0.74
     homoto
    -0.74
    Zz
    -0.72
    dataSource
    -0.72
    OMO
    -0.71
     Kunde
    -0.71
    POSITIVE LOGITS
     it
    1.04
     amends
    1.02
     plays
    0.98
    IMPACT
    0.95
     '',
    0.92
     impact
    0.91
     Plays
    0.90
    impact
    0.83
    ())
    0.81
     noise
    0.79
    Activations Density 0.015%

    No Known Activations