© 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. 23966
    Prev
    Next
    INDEX
    Explanations

    the X

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

    describes how

    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
    itative
    0.48
     spots
    0.44
     Liver
    0.44
     Flows
    0.43
     だ
    0.41
    昔
    0.41
     Of
    0.41
     liver
    0.41
    ᆸ
    0.41
     Having
    0.41
    POSITIVE LOGITS
    評價
    0.49
    preview
    0.48
    जेंट
    0.47
     gratuitos
    0.47
     કાર્યવાહી
    0.45
     бесплатно
    0.44
     бясплатна
    0.43
    免費
    0.43
     आयोजित
    0.42
    ρού
    0.42
    Activations Density 0.000%

    No Known Activations