© 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. 89711
    Prev
    Next
    INDEX
    Explanations

    sit with

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

    state within context

    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
     browser
    0.50
    ડ
    0.47
     path
    0.47
     conductivity
    0.47
     filamentous
    0.47
     concentra
    0.47
     plane
    0.46
    য়েছে
    0.46
    Uc
    0.45
     condu
    0.45
    POSITIVE LOGITS
     Arias
    0.46
     solos
    0.46
     Garry
    0.44
    मंत्री
    0.44
    k
    0.44
    kaisi
    0.42
     gjennom
    0.42
     deshalb
    0.41
    rements
    0.41
    fohlen
    0.41
    Activations Density 0.001%

    No Known Activations