© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49108
    Prev
    Next
    INDEX
    Explanations

    concepts, states, actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rashes
    0.60
     psychologists
    0.55
    ３
    0.55
     circus
    0.52
     cinematography
    0.49
     languages
    0.49
     preschoolers
    0.49
     landfills
    0.48
     psyche
    0.48
     townships
    0.48
    POSITIVE LOGITS
    ar
    0.59
     даже
    0.58
    ،
    0.55
    that
    0.54
    ());
    0.53
    ที่
    0.52
     दैट
    0.52
    rijving
    0.52
    เขา
    0.50
    Arm
    0.50
    Activations Density 0.110%

    No Known Activations