© 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. 77452
    Prev
    Next
    INDEX
    Explanations

    watching future culture

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

    Stephanie's character traits and actions

    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
     subpar
    0.44
    สุ
    0.44
    。</
    0.42
     explanatory
    0.41
    explicit
    0.41
     computation
    0.41
    วิ
    0.41
    .</
    0.40
    legung
    0.40
     алгорит
    0.39
    POSITIVE LOGITS
    atherapy
    0.45
     Dementia
    0.43
     síntomas
    0.42
    叐
    0.42
     televisión
    0.42
     dementia
    0.41
     prácticamente
    0.40
     Cruises
    0.40
     Rott
    0.40
     divent
    0.40
    Activations Density 0.001%

    No Known Activations