© 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. 16895
    Prev
    Next
    INDEX
    Explanations

    asking for details or code

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

    Markdown bolded section headers and emphasis markers used to introduce structured bullet points or prompts.

    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
     febbraio
    0.40
     Touch
    0.37
    菏
    0.36
     February
    0.36
    exon
    0.35
     March
    0.34
     touched
    0.34
     touch
    0.34
    лян
    0.34
     पहली
    0.34
    POSITIVE LOGITS
     предусматри
    0.43
     অন্যান্য
    0.41
     diğer
    0.39
     ఇతర
    0.38
    golang
    0.37
    amız
    0.37
    캠
    0.36
     prevista
    0.35
    በ
    0.35
     માંગ
    0.35
    Activations Density 0.000%

    No Known Activations