© 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. 49541
    Prev
    Next
    INDEX
    Explanations

    finding useful

    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
    iega
    -0.82
    SEARCH
    -0.81
     boden
    -0.78
    iden
    -0.76
     Stolz
    -0.75
    arka
    -0.74
     וּ
    -0.73
    searched
    -0.73
     ū
    -0.72
    <0x97>
    -0.72
    POSITIVE LOGITS
     found
    5.28
     find
    5.19
     finds
    4.59
    find
    4.34
    Find
    4.06
     finding
    3.89
     Find
    3.84
    found
    3.63
    Found
    3.42
     FIND
    3.36
    Activations Density 0.102%

    No Known Activations