© 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. 99352
    Prev
    Next
    INDEX
    Explanations

    querying data streams

    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
    degrad
    -0.84
    쌤
    -0.74
    COUVER
    -0.72
     Physicians
    -0.71
     DMS
    -0.70
    ENAME
    -0.69
    succeeded
    -0.69
    肥
    -0.68
     someplace
    -0.67
    čit
    -0.66
    POSITIVE LOGITS
     verbs
    0.93
    verb
    0.89
    river
    0.88
    VERB
    0.85
     actor
    0.85
     verb
    0.85
     targets
    0.82
     гла
    0.79
    zul
    0.76
     herramienta
    0.75
    Activations Density 0.018%

    No Known Activations