© 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. 1257
    Prev
    Next
    INDEX
    Explanations

    instances of narrative descriptions and emotionally charged language.

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

    lists and examples

    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
     jeweiligen
    0.21
    .
    0.20
    0.18
    0.17
    ↵↵↵↵
    0.17
    }
    0.17
    َّ
    0.16
    0.16
    0.16
    ogeneity
    0.16
    POSITIVE LOGITS
     например
    0.23
     तसेच
    0.22
     zatim
    0.21
     oppure
    0.21
     которые
    0.21
    א
    0.21
     или
    0.21
    したり
    0.21
    或是
    0.20
    רי
    0.20
    Activations Density 1.390%

    No Known Activations