© 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-65K
    7. 2772
    Prev
    Next
    INDEX
    Explanations

    emotional or philosophical themes related to human experiences and interactions.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    determiner followed by noun

    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
    a
    0.44
    ol
    0.38
    <0x80>
    0.38
    A
    0.38
    on
    0.37
    7
    0.37
    ig
    0.36
    8
    0.36
    an
    0.35
    n
    0.35
    POSITIVE LOGITS
     whatnot
    0.40
     حتی
    0.40
     hatta
    0.38
     która
    0.38
     farce
    0.38
     ganas
    0.38
     heartache
    0.38
     ت
    0.37
     जिसे
    0.36
     التي
    0.36
    Activations Density 0.263%

    No Known Activations