© 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. 34202
    Prev
    Next
    INDEX
    Explanations

    current thinking explained

    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
    t
    0.57
     entities
    0.54
    腃
    0.53
     interag
    0.52
     routing
    0.52
     universit
    0.50
     robotics
    0.50
    지는
    0.50
     část
    0.49
     части
    0.49
    POSITIVE LOGITS
    к
    0.82
    ab
    0.72
    am
    0.71
    ed
    0.69
    ي
    0.68
    𝗱
    0.66
    q
    0.64
    ın
    0.64
    ی
    0.64
    on
    0.63
    Activations Density 0.002%

    No Known Activations