© 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. 44
    Prev
    Next
    INDEX
    Explanations

    explaining steps or instructions

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

    Markdown-style formatting cues—especially bolded section headers and bullet-list emphasis.

    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
     (
    0.20
     ("
    0.19
     (_
    0.18
     and
    0.18
    ")]
    0.18
    /
    0.18
          
    0.18
     （
    0.18
    および
    0.18
         
    0.18
    POSITIVE LOGITS
     It
    0.22
    It
    0.21
     यह
    0.20
    ungnya
    0.19
     it
    0.19
    यह
    0.19
     этого
    0.19
    Could
    0.19
     большинство
    0.19
    это
    0.18
    Activations Density 3.499%

    No Known Activations