© 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. 10214
    Prev
    Next
    INDEX
    Explanations

    directly followed by location or action

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

    Hydrogen, NFTs

    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
    Violence
    0.48
    Descrição
    0.46
     violência
    0.46
    犯罪
    0.45
     Bankers
    0.44
    Describes
    0.42
    撚
    0.42
    Cells
    0.42
     चेहरे
    0.42
     Fracture
    0.42
    POSITIVE LOGITS
     высокие
    0.51
    െ
    0.50
    ートル
    0.50
     梅
    0.48
     pamoja
    0.47
     accentuate
    0.47
     मैन
    0.47
    െയുള്ള
    0.47
    bos
    0.45
    lığı
    0.45
    Activations Density 0.000%

    No Known Activations