© 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. 2728
    Prev
    Next
    INDEX
    Explanations

    sequences that involve structured documentation or formal communication.

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

    end of phrases

    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
     tubules
    0.43
     hydrochloric
    0.41
    紂
    0.41
     timescale
    0.40
     isom
    0.40
    যানী
    0.39
     appunto
    0.39
     proteins
    0.39
     shackles
    0.39
     radiographs
    0.39
    POSITIVE LOGITS
     Experienced
    0.38
    ↵
    0.37
     Attend
    0.37
     Editar
    0.37
    Please
    0.36
     Concerns
    0.36
    Attend
    0.36
     Recuer
    0.36
     Statement
    0.35
     एक्
    0.35
    Activations Density 0.450%

    No Known Activations