© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 33108
    Prev
    Next
    INDEX
    Explanations

    role-playing personas

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

    roleplay-style stage directions—emotive physical actions and gestures described in asterisks.

    oai_token-act-pair · gpt-5Triggered by @yooniel31
    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
    0.71
     was
    0.64
    <0x80>
    0.58
    (
    0.57
    on
    0.57
     caiu
    0.55
    簋
    0.54
     был
    0.54
    ven
    0.53
    했다
    0.53
    POSITIVE LOGITS
     organisms
    0.61
     capacities
    0.61
    ↵
    0.61
     Strength
    0.60
     canisters
    0.59
     units
    0.59
     Units
    0.59
     strength
    0.58
    üğünüz
    0.58
     Acceptance
    0.57
    Activations Density 0.016%

    No Known Activations