© 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. 1272
    Prev
    Next
    INDEX
    Explanations

    narrative elements in story-like contexts.

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

    and as

    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
     وأ
    0.31
     和
    0.30
    ↵↵
    0.29
     و
    0.26
     καὶ
    0.25
     والم
    0.24
     三
    0.24
     وتم
    0.24
     [])
    0.23
     bitmap
    0.23
    POSITIVE LOGITS
     importantly
    0.42
     crucially
    0.34
     вполне
    0.33
     oczywiście
    0.32
     म्हणूनच
    0.32
     nadie
    0.31
    ppure
    0.31
     furthermore
    0.31
     frankly
    0.30
     многое
    0.30
    Activations Density 0.568%

    No Known Activations