© 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. 27147
    Prev
    Next
    INDEX
    Explanations

    sequences often starting with "to"

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

    incidents, components, environmental, labor, mental, physical

    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
    н
    0.59
    >);
    0.49
    nahm
    0.48
    тер
    0.48
    днев
    0.47
    ត្រូវការ
    0.47
     আরাম
    0.46
    叉
    0.46
    Quit
    0.45
    mäß
    0.45
    POSITIVE LOGITS
     Nir
    0.52
     blazer
    0.52
     tenor
    0.50
     bother
    0.49
     perfetto
    0.49
     photod
    0.49
     dale
    0.49
     agron
    0.48
     culprit
    0.48
     bittersweet
    0.47
    Activations Density 0.000%

    No Known Activations