© 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. 61133
    Prev
    Next
    INDEX
    Explanations

    internal repair and decoration

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

    titles and names

    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
    Em
    0.55
     reten
    0.50
    \
    0.46
    Consider
    0.45
    יי
    0.45
    nden
    0.44
     faci
    0.44
    考え
    0.44
    $\
    0.44
    "
    0.44
    POSITIVE LOGITS
     dispos
    0.54
     dispositions
    0.54
     salted
    0.52
     edibles
    0.51
     idioms
    0.51
     thermocou
    0.50
    منٹ
    0.49
     napkins
    0.49
     dukkham
    0.49
     oaths
    0.48
    Activations Density 0.000%

    No Known Activations