© 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. 10-GEMMASCOPE-RES-131K
    7. 8954
    Prev
    Next
    INDEX
    Explanations

    code keywords and syntax

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron responds to all-caps section or transition markers (e.g. “END VIDEO CLIP” or “Transmission”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     also
    -1.98
     this
    -1.96
     to
    -1.95
     you
    -1.66
    estero
    -1.37
     were
    -1.36
     and
    -1.33
    総評
    -1.31
     également
    -1.31
     NOT
    -1.31
    POSITIVE LOGITS
    3
    1.65
    el
    1.55
    unea
    1.48
    igned
    1.48
    us
    1.45
    }
    1.42
    id
    1.41
    褙
    1.41
    брати
    1.41
    ah
    1.41
    Activations Density 0.007%

    No Known Activations