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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3633
    Prev
    Next
    INDEX
    Explanations

    hyperparameters

    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
     (
    0.55
     that
    0.41
     άνθρω
    0.38
    iejsc
    0.37
     Muay
    0.36
    ’
    0.36
    ierzchn
    0.36
     владе
    0.36
    leza
    0.36
    that
    0.35
    POSITIVE LOGITS
    ة
    0.49
     esempio
    0.43
     unei
    0.43
     の
    0.43
     egy
    0.41
     eine
    0.41
    q
    0.41
    した
    0.41
     হয়েছিল
    0.41
    ിൽ
    0.41
    Activations Density 2.519%

    No Known Activations