© 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. 1212
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions and events in fictional narratives.

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

    `t` or `1`

    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
     physiologic
    0.23
     antigenic
    0.22
     cytokinin
    0.22
     boutons
    0.22
     endothelium
    0.21
    ،
    0.21
    }+...
    0.21
     raisins
    0.21
     subdir
    0.21
     effluents
    0.20
    POSITIVE LOGITS
    and
    0.35
    P
    0.34
    S
    0.30
    online
    0.30
    In
    0.28
    or
    0.27
    D
    0.27
    am
    0.27
    M
    0.27
    H
    0.27
    Activations Density 5.669%

    No Known Activations