© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39911
    Prev
    Next
    INDEX
    Explanations

    quoting or cited speech

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

    quoting text or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    renzia
    0.61
    b
    0.61
     embankment
    0.61
     Сасик
    0.59
    smoothed
    0.58
    descriptors
    0.57
    sibling
    0.55
    h
    0.55
    geojson
    0.54
    }]_{
    0.54
    POSITIVE LOGITS
    '
    0.98
    1
    0.91
    Quote
    0.87
     Quote
    0.86
     quote
    0.81
    9
    0.80
    Quotes
    0.79
    7
    0.78
     quotes
    0.76
    5
    0.75
    Activations Density 0.015%

    No Known Activations