© 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. 16-GEMMASCOPE-2-RES-262K
    4. 40819
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs

    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_16_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
    ความเป็น
    0.78
     ጭ
    0.71
    ož
    0.71
     detoxification
    0.70
     mocy
    0.70
    ziehungen
    0.68
     exuberant
    0.67
    력이
    0.66
     работой
    0.65
     Fukuoka
    0.65
    POSITIVE LOGITS
    s
    1.20
    k
    1.02
    j
    1.02
    م
    1.02
    ik
    0.99
    b
    0.91
    ت
    0.91
    z
    0.89
    te
    0.88
    sch
    0.86
    Activations Density 0.039%

    No Known Activations