© 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. 220702
    Prev
    Next
    INDEX
    Explanations

    supplier of components

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

    words like 'liga' and 'technical'

    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
    alcohol
    0.44
    af
    0.44
    알
    0.44
    ;,
    0.43
    alcool
    0.43
    ;-
    0.43
     portanto
    0.43
     encapsulated
    0.43
    ,..
    0.42
     announc
    0.42
    POSITIVE LOGITS
    माने
    0.48
     هزینه
    0.43
     dxe
    0.41
    נית
    0.41
     යුතුය
    0.41
     سلامه
    0.41
    ujah
    0.40
    沓
    0.40
    십시오
    0.40
    TAGE
    0.40
    Activations Density 0.001%

    No Known Activations