© 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. 98917
    Prev
    Next
    INDEX
    Explanations

    activity is, angel came, protagonist to

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

    problems, questions, and riddles

    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
    摷
    0.56
    箴
    0.54
    Como
    0.46
    s
    0.46
    陛下
    0.45
    ཋ
    0.45
    自己的
    0.44
    ాము
    0.43
    冼
    0.42
    FIND
    0.42
    POSITIVE LOGITS
    फना
    0.47
    storybook
    0.43
    PointCloud
    0.43
     palk
    0.43
     couldn
    0.42
    ုန်
    0.41
     शोभा
    0.41
     असंभव
    0.41
     चै
    0.41
    iegen
    0.40
    Activations Density 0.000%

    No Known Activations