© 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. 14360
    Prev
    Next
    INDEX
    Explanations

    dictionary keys and programming options

    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
     {{
    0.48
    {{
    0.47
    ("|
    0.41
    袂
    0.40
     ຮ
    0.39
    加上
    0.39
     {'
    0.38
     Tü
    0.37
    +(
    0.37
    ('|
    0.37
    POSITIVE LOGITS
     keys
    0.63
    Keys
    0.59
     Keys
    0.58
    key
    0.56
     key
    0.54
    キー
    0.52
     chiave
    0.52
     chave
    0.51
     kunci
    0.51
    钥匙
    0.51
    Activations Density 0.001%

    No Known Activations