© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32088
    Prev
    Next
    INDEX
    Explanations

    exclusions and exemptions

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

    tokens that open the model's explanatory reply—short conversational lead-ins or first‑person pronouns used when the assistant begins answering.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     นี่
    0.44
    these
    0.42
    これは
    0.41
     እነዚህ
    0.41
     tämä
    0.39
    
    0.39
    subtree
    0.38
     இரண்டு
    0.38
    これらの
    0.38
    iterranée
    0.38
    POSITIVE LOGITS
    ,
    0.40
     exclusions
    0.38
     angin
    0.37
     randomised
    0.36
     heuristics
    0.36
     decree
    0.32
     efficiently
    0.32
     specialised
    0.32
     reactivity
    0.32
     exemptions
    0.32
    Activations Density 0.113%

    No Known Activations