© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3746
    Prev
    Next
    INDEX
    Explanations

    character profiles and personalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     postponement
    0.81
     sky
    0.80
     Venue
    0.74
     Dolby
    0.72
     skies
    0.71
     venues
    0.70
    orrag
    0.70
    瘙
    0.69
    venue
    0.69
     हाईवे
    0.69
    POSITIVE LOGITS
     personality
    2.03
     Personality
    1.83
     profile
    1.75
     personalities
    1.74
    Personality
    1.73
    personality
    1.67
     profiles
    1.64
     Profile
    1.63
     personalidad
    1.63
     persona
    1.62
    Activations Density 1.176%

    No Known Activations