© 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. 14448
    Prev
    Next
    INDEX
    Explanations

    Finnish words and grammar

    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
     ग
    0.64
     ___
    0.58
     Baal
    0.57
     LEDs
    0.56
    '
    0.56
     мир
    0.55
     Ravi
    0.54
     G
    0.54
    প্র
    0.54
     Canadian
    0.54
    POSITIVE LOGITS
     kaikki
    1.22
     suunn
    1.21
     myös
    1.19
     pää
    1.19
     palvel
    1.19
     käyt
    1.16
     hyvä
    1.16
     ensimmä
    1.12
     esimerkiksi
    1.12
     että
    1.11
    Activations Density 0.004%

    No Known Activations