© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 143023
    Prev
    Next
    INDEX
    Explanations

    bottlenecks, engineering, grants, Timor

    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
     brightest
    0.50
    }=(
    0.50
    ides
    0.50
     croche
    0.50
     warring
    0.49
    <unused657>
    0.48
     légion
    0.48
    RAchievement
    0.47
     penguins
    0.47
     peacock
    0.46
    POSITIVE LOGITS
    т
    0.63
    You
    0.52
    ت
    0.50
     т
    0.48
     or
    0.48
    اه
    0.47
    त
    0.47
    ，
    0.47
    ،
    0.46
    ת
    0.46
    Activations Density 0.000%

    No Known Activations