© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146639
    Prev
    Next
    INDEX
    Explanations

    personality

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    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
     dynamic
    0.42
    ंसद
    0.38
    Dynamic
    0.36
    গঠনিক
    0.36
    ])[
    0.36
     Dynamic
    0.35
    PathComponent
    0.35
     energético
    0.35
    '])[
    0.35
     बुक
    0.35
    POSITIVE LOGITS
     personality
    1.67
     Personality
    1.48
    personality
    1.48
    Personality
    1.43
     personalidade
    1.15
     personalidad
    1.09
    性格
    1.05
     personnalité
    1.05
     personalità
    1.04
     व्यक्तित्व
    0.96
    Activations Density 0.006%

    No Known Activations