© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31840
    Prev
    Next
    INDEX
    Explanations

    technical or factual descriptions

    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_40_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
     metų
    0.43
     reborn
    0.43
     حساس
    0.42
     kota
    0.40
     महीना
    0.39
    Expires
    0.38
     sensiblement
    0.38
    ୀ
    0.38
     सीड्स
    0.37
     Guid
    0.37
    POSITIVE LOGITS
     pamo
    0.40
    科学
    0.37
    relle
    0.36
    ฬ
    0.36
     поза
    0.35
    えば
    0.34
     براہ
    0.34
     вя
    0.34
    Designs
    0.34
    स्टन
    0.34
    Activations Density 0.000%

    No Known Activations