Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 18444
    Prev
    Next
    INDEX
    Explanations

    old man storyteller

    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_40_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
    Jessica
    0.51
     Jessica
    0.47
     Executives
    0.45
     glamorous
    0.44
     caviar
    0.43
    Jason
    0.42
     Vanessa
    0.42
    蘅
    0.42
     coworking
    0.42
    Chase
    0.41
    POSITIVE LOGITS
    👵
    0.71
     Mama
    0.66
     peasant
    0.66
     village
    0.64
     Grandmother
    0.61
    👴
    0.60
     farmer
    0.59
     grandmother
    0.59
     Grandma
    0.59
    peasants
    0.59
    Activations Density 0.010%

    No Known Activations