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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 28
    Prev
    Next
    INDEX
    Explanations

    questions about gifts or context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_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
     yıldır
    0.29
     inhibit
    0.28
     stoichi
    0.28
    ್
    0.28
     nog
    0.27
     بالکل
    0.27
    splitLength
    0.27
     ஒரே
    0.27
     mò
    0.27
     esters
    0.26
    POSITIVE LOGITS
    This
    0.33
    Which
    0.32
    При
    0.31
     What
    0.30
    https
    0.30
     Introduction
    0.30
    он
    0.30
    у
    0.29
    पांच
    0.29
     При
    0.29
    Activations Density 0.492%

    No Known Activations