© 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. 189699
    Prev
    Next
    INDEX
    Explanations

    driving and related information

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

    integrating forms and foreign policy

    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
     ді
    0.47
     court
    0.45
     treasury
    0.45
     interpretations
    0.43
     ಕೋ
    0.43
     אך
    0.42
     但
    0.42
     berupa
    0.41
     hatta
    0.41
    γη
    0.40
    POSITIVE LOGITS
    aturated
    0.48
    Características
    0.46
    蚜
    0.44
    Algorithm
    0.43
     மாதிரி
    0.43
    愈
    0.43
    自然
    0.42
     Detecting
    0.42
    Improving
    0.42
    预防
    0.41
    Activations Density 0.001%

    No Known Activations