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-262K
    4. 374
    Prev
    Next
    INDEX
    Explanations

    [Keyword] placeholders

    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_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
     loadAnimation
    0.38
    ₂+
    0.36
     fungicides
    0.36
     amplit
    0.36
     chemotherapy
    0.36
     dialysis
    0.35
    কথা
    0.35
     sông
    0.35
    LensFlare
    0.34
     tannin
    0.34
    POSITIVE LOGITS
     ,
    0.46
     .
    0.37
     .,
    0.35
    which
    0.35
     which
    0.34
     जिसमे
    0.33
    If
    0.33
     If
    0.32
    May
    0.32
    Mais
    0.32
    Activations Density 0.003%

    No Known Activations