© 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. 117446
    Prev
    Next
    INDEX
    Explanations

    factorslinestringinfiltrationend

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

    SQL database

    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
     américains
    0.55
     Serviço
    0.50
    戦争
    0.49
    姆
    0.49
    écies
    0.49
     Muit
    0.49
    昨年
    0.48
     amerikanischen
    0.48
    擎
    0.48
     hoteles
    0.47
    POSITIVE LOGITS
    end
    0.50
     crystall
    0.49
     crow
    0.47
    iboard
    0.43
    unbind
    0.43
    akura
    0.43
    divided
    0.42
    ifi
    0.42
     grazing
    0.42
    intersect
    0.42
    Activations Density 0.000%

    No Known Activations