© 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. 35014
    Prev
    Next
    INDEX
    Explanations

    SUMAR Excel, atmosphere, Cell Structure

    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
     iphdr
    0.44
    IEEE
    0.41
    OGND
    0.41
    INE
    0.40
    тие
    0.40
    UUID
    0.39
    гава
    0.39
    ק
    0.39
    に関して
    0.38
    炀
    0.38
    POSITIVE LOGITS
     empathy
    0.50
    touch
    0.48
     cidades
    0.46
    one
    0.46
    etrics
    0.45
     aspirations
    0.45
     Promises
    0.45
    ır
    0.43
     decisive
    0.43
     ér
    0.43
    Activations Density 0.001%

    No Known Activations