© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 2346
    Prev
    Next
    INDEX
    Explanations

    expressions of casual interaction and conversational content.

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

    adverbs of certainty, emphasis, or likelihood

    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
    (
    0.47
    /
    0.36
     ion
    0.35
    :
    0.34
     والك
    0.33
     monotonic
    0.33
     rotor
    0.33
     windings
    0.33
     
    0.32
     synchronously
    0.32
    POSITIVE LOGITS
     אבל
    0.40
     लेकिन
    0.39
     কিন্তু
    0.39
    ė
    0.39
    hhh
    0.37
    。。
    0.36
    !।
    0.36
    तमंद
    0.36
    מ
    0.36
     பத்திர
    0.35
    Activations Density 0.179%

    No Known Activations