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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18248
    Prev
    Next
    INDEX
    Explanations

    supply chains, environments, stadt

    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_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
     shoulders
    0.49
     naturais
    0.46
     hibiscus
    0.46
     shrubs
    0.44
    癒
    0.44
     ribbons
    0.44
     caballos
    0.43
    Референце
    0.43
     ग्रामीणों
    0.42
     umbrellas
    0.42
    POSITIVE LOGITS
    :
    0.47
    mpeg
    0.45
    :"
    0.45
    тың
    0.44
    sembly
    0.44
    ające
    0.43
    .:
    0.43
    ('
    0.42
     sitcom
    0.41
    dit
    0.41
    Activations Density 0.003%

    No Known Activations