© 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. 78946
    Prev
    Next
    INDEX
    Explanations

    found, has, had, just

    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
    suchen
    -1.05
    hellip
    -0.95
    (…)
    -0.92
    ܞ
    -0.90
    能
    -0.90
    wendig
    -0.87
    ________,
    -0.86
     SINCE
    -0.85
    ÍS
    -0.85
    tempt
    -0.84
    POSITIVE LOGITS
     found
    2.84
     hit
    2.13
     struck
    1.75
     Found
    1.75
    Found
    1.70
    found
    1.66
     finally
    1.62
    hit
    1.54
     gevonden
    1.42
     discovered
    1.40
    Activations Density 0.050%

    No Known Activations