© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 191002
    Prev
    Next
    INDEX
    Explanations

    by value, or spooky it

    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
    -
    0.50
     Latin
    0.45
     RE
    0.43
    Latin
    0.42
    че
    0.42
     brilliant
    0.40
    2
    0.40
    6
    0.40
    8
    0.40
    ERS
    0.39
    POSITIVE LOGITS
    ススメ
    0.43
    stärke
    0.42
    ٬
    0.42
    abhavam
    0.41
     বেশী
    0.41
    দোষ
    0.41
    謗
    0.41
    বৃন্দ
    0.40
    strconv
    0.40
    abhavo
    0.40
    Activations Density 0.003%

    No Known Activations