Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12282
    Prev
    Next
    INDEX
    Explanations

    quoting numbers and symbols

    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
    ➜
    0.43
    FERRED
    0.42
    UTURE
    0.42
    廡
    0.42
    fully
    0.41
     hãy
    0.40
     समुद्र
    0.40
    lodash
    0.40
    ieson
    0.40
    niają
    0.40
    POSITIVE LOGITS
     education
    0.36
     greats
    0.34
    킹
    0.34
     ^{
    0.34
    ถี่
    0.34
    帧
    0.33
    زر
    0.33
     spitting
    0.33
     "^
    0.32
     greatest
    0.32
    Activations Density 0.001%

    No Known Activations