© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 11793
    Prev
    Next
    INDEX
    Explanations

    listing multiple concepts

    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
    (
    0.29
    ,
    0.26
    的
    0.23
     also
    0.23
     actually
    0.22
     också
    0.22
     definitely
    0.22
     than
    0.21
     arguably
    0.21
     include
    0.21
    POSITIVE LOGITS
    राहुल
    0.24
     پیسې
    0.24
    Raymond
    0.23
     tourisme
    0.23
    
    0.23
     بیاکتنې
    0.23
    その他
    0.22
     littérature
    0.22
     വൈദ്യുതി
    0.21
     religion
    0.21
    Activations Density 0.087%

    No Known Activations