© 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. 29075
    Prev
    Next
    INDEX
    Explanations

    the number 8

    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
     sacking
    0.40
     flound
    0.40
    ්ර
    0.40
     kore
    0.39
    逦
    0.39
    )`;
    0.38
    버
    0.37
     entferne
    0.37
     humbling
    0.37
    ◅
    0.37
    POSITIVE LOGITS
     आठ
    0.43
     Creo
    0.41
     este
    0.40
     восем
    0.39
     estética
    0.39
     съ
    0.38
     (\
    0.38
     на
    0.38
    āli
    0.38
     si
    0.37
    Activations Density 0.038%

    No Known Activations