© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 27359
    Prev
    Next
    INDEX
    Explanations

    creative project and presentation content

    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_31_width_65k_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
    饕
    0.44
    workouts
    0.40
    トレーニング
    0.39
    khane
    0.39
     engagement
    0.39
     immediatamente
    0.39
    讳
    0.39
    ന്ത്രി
    0.38
     workouts
    0.37
    ᡧ
    0.37
    POSITIVE LOGITS
     Presentation
    0.71
     Creativity
    0.70
     creatividad
    0.69
     presentation
    0.66
     Presentations
    0.66
     kreativ
    0.63
     creativity
    0.60
     Poster
    0.59
    Presentation
    0.57
     poster
    0.55
    Activations Density 0.097%

    No Known Activations