© 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. 14598
    Prev
    Next
    INDEX
    Explanations

    virtual desktop and apps

    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
    াইল
    0.40
     molto
    0.39
     vegetal
    0.39
     그래도
    0.39
    爬
    0.39
    蔵
    0.38
     הרבה
    0.38
     বন্যা
    0.38
     संत
    0.37
     swan
    0.37
    POSITIVE LOGITS
     Ember
    0.81
    ember
    0.70
     ember
    0.70
    EMBER
    0.55
    hbs
    0.53
    embro
    0.50
    didReceive
    0.48
     {{
    0.47
     embers
    0.46
    queryParams
    0.45
    Activations Density 0.002%

    No Known Activations