© 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. 1466
    Prev
    Next
    INDEX
    Explanations

    suffixation

    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
    ot
    0.58
    on
    0.55
    ar
    0.42
    a
    0.41
     a
    0.39
    I
    0.38
    r
    0.38
    ner
    0.36
    eing
    0.36
    os
    0.35
    POSITIVE LOGITS
     be
    0.52
     or
    0.47
     academies
    0.45
    ിൽ
    0.43
    ہ
    0.43
    カ
    0.43
    이지만
    0.42
    の
    0.42
    ﭜ
    0.42
    ری
    0.40
    Activations Density 0.162%

    No Known Activations