© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 69758
    Prev
    Next
    INDEX
    Explanations

    stir after

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

    state, summary, lead, AWS

    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
    骈
    0.48
     Ba
    0.46
     Ба
    0.45
     NOTE
    0.45
     
    0.45
     Ordinance
    0.45
     quatro
    0.44
     Fannie
    0.43
     Va
    0.43
     Give
    0.43
    POSITIVE LOGITS
    agangan
    0.52
    kag
    0.47
    opacity
    0.46
    🧺
    0.46
    DESIGN
    0.45
    ES
    0.45
    US
    0.45
    distance
    0.45
    രണ
    0.45
    forRoot
    0.44
    Activations Density 0.001%

    No Known Activations