© 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. 3187
    Prev
    Next
    INDEX
    Explanations

    . array/* arraysince array

    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
    ULING
    -0.81
     doable
    -0.77
     conveyed
    -0.76
    ܪ
    -0.76
    oole
    -0.75
    tabilité
    -0.74
     buddies
    -0.74
     substrates
    -0.73
    场面
    -0.73
    ੈ
    -0.72
    POSITIVE LOGITS
    interpolate
    0.84
     objed
    0.83
    VERSION
    0.82
    pektor
    0.76
     draußen
    0.74
    ಠ
    0.73
     hypertrophy
    0.73
    blech
    0.72
    terr
    0.71
    inerario
    0.71
    Activations Density 0.038%

    No Known Activations