© 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. 159274
    Prev
    Next
    INDEX
    Explanations

    health, emergency, lab, digital

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

    document attachment or addition

    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
    José
    0.46
    Dig
    0.46
    zers
    0.44
    Գ
    0.44
    testGet
    0.44
    也可
    0.44
    hg
    0.43
     மேலும்
    0.43
     dug
    0.43
    Provision
    0.43
    POSITIVE LOGITS
    িয়ন
    0.46
    斜
    0.46
     muzzle
    0.44
    ENSION
    0.43
     Durchmesser
    0.43
    ionale
    0.42
     Szk
    0.42
     oxidation
    0.42
    적인
    0.42
     bonsai
    0.42
    Activations Density 0.000%

    No Known Activations