© 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. 411
    Prev
    Next
    INDEX
    Explanations

    detail or detailed information

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

    detailed

    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
     Sea
    0.66
     o
    0.64
     two
    0.61
     bottle
    0.61
     Penguin
    0.61
     HEP
    0.60
     Penguins
    0.60
     r
    0.59
     tokamak
    0.59
     SEA
    0.59
    POSITIVE LOGITS
    细节
    1.56
     detall
    1.34
    details
    1.33
     detalle
    1.33
     detalhes
    1.31
     detalles
    1.29
     détails
    1.29
     дета
    1.29
     детали
    1.29
     détaillée
    1.28
    Activations Density 0.069%

    No Known Activations