© 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-262K
    7. 10964
    Prev
    Next
    INDEX
    Explanations

    starting or continuation of phrases

    np_acts-logits-general · gemini-2.5-flash-lite

    discourse-structuring cue words that signal transitions, sections, or evaluative headings in formal or expository writing.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     Sustainable
    0.32
     wszystkim
    0.32
    ESSAGE
    0.32
    樹
    0.32
     rendszer
    0.31
    eluarkan
    0.31
     Lockdown
    0.31
     ಚುನ
    0.31
    ल्लिंग
    0.30
    ৃত্বে
    0.30
    POSITIVE LOGITS
     the
    0.51
     their
    0.40
    said
    0.38
     மட்டுமல்ல
    0.37
     it
    0.36
    р
    0.35
     brazen
    0.35
     THE
    0.34
    the
    0.34
    🔩
    0.34
    Activations Density 0.695%

    No Known Activations