Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 7762
    Prev
    Next
    INDEX
    Explanations

    likelihood

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

    section headers and list-structuring labels that signal organized, categorized explanations or guides.

    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
     QString
    0.23
     operand
    0.22
     cardinality
    0.22
     abhid
    0.22
     దాని
    0.21
     Portanto
    0.21
     Ispol
    0.21
     wobei
    0.21
     Painlev
    0.21
     malonyl
    0.21
    POSITIVE LOGITS
    Corporate
    0.18
    ки
    0.17
    micro
    0.17
    popular
    0.17
    early
    0.17
    C
    0.17
    policies
    0.17
    smart
    0.16
    Luxury
    0.16
    R
    0.16
    Activations Density 1.937%

    No Known Activations