© 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. 73980
    Prev
    Next
    INDEX
    Explanations

    rights, optimization, cooking, on

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

    technical and descriptive contexts

    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
    вной
    0.47
    giene
    0.46
    ஞான
    0.45
    ֵ
    0.45
    u
    0.45
    ﺻ
    0.44
    담당
    0.43
    ペア
    0.42
    haut
    0.42
     держави
    0.42
    POSITIVE LOGITS
     entweder
    0.50
     It
    0.49
    ึก
    0.47
     ameri
    0.47
     choque
    0.47
     But
    0.44
     amerikan
    0.44
    ,?
    0.43
     In
    0.43
    нены
    0.43
    Activations Density 0.002%

    No Known Activations