© 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. 2191
    Prev
    Next
    INDEX
    Explanations

    narrative elements and character development within a story.

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

    seeing and finding

    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
    ックス
    0.22
    섰
    0.21
    єю
    0.20
    with
    0.20
    อร์
    0.19
    وي
    0.19
    ็ต
    0.19
     medizin
    0.18
    يزات
    0.18
    ニア
    0.18
    POSITIVE LOGITS
     them
    0.30
     him
    0.28
     it
    0.28
     firsthand
    0.25
     👀
    0.24
     people
    0.22
     તેને
    0.22
     the
    0.22
     patterns
    0.22
     claramente
    0.21
    Activations Density 0.356%

    No Known Activations