© 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. 226321
    Prev
    Next
    INDEX
    Explanations

    bridge connection

    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
    発
    0.46
    obt
    0.44
     chol
    0.43
    OS
    0.42
    ubert
    0.42
    DP
    0.42
    IU
    0.41
    olic
    0.41
    JS
    0.40
    ↵
    0.40
    POSITIVE LOGITS
     franchisees
    0.48
     underlines
    0.48
     pathogenicity
    0.46
     immunocom
    0.46
     مریض
    0.46
     epidemics
    0.46
     italics
    0.46
     pathogens
    0.46
     neonatal
    0.45
    ものの
    0.45
    Activations Density 0.001%

    No Known Activations