© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 21292
    Prev
    Next
    INDEX
    Explanations

    method followed by other

    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
     velocities
    0.54
     erklärte
    0.50
     світі
    0.49
    砀
    0.48
     phd
    0.48
     بيكون
    0.47
    WithFieldContext
    0.47
     गेंदबाज
    0.47
    []>
    0.46
     lefty
    0.46
    POSITIVE LOGITS
    ier
    0.55
    νο
    0.48
    ኵ
    0.46
    ulating
    0.45
    using
    0.44
    வர
    0.43
    ாலும்
    0.43
     ببین
    0.43
    getExtension
    0.43
    ikti
    0.43
    Activations Density 0.000%

    No Known Activations