© 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. 31-GEMMASCOPE-2-RES-262K
    7. 78810
    Prev
    Next
    INDEX
    Explanations

    complex numbers, self-love, 2

    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_31_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
    owania
    0.46
    ഓ
    0.46
    സീ
    0.46
     никаких
    0.45
    叽
    0.44
    广告
    0.44
    农
    0.42
     topik
    0.42
    ب
    0.41
    小学
    0.41
    POSITIVE LOGITS
     suspension
    0.46
     Cy
    0.45
    ແລະ
    0.44
     augment
    0.43
     salute
    0.43
     John
    0.42
     safeguard
    0.42
     hydroelectric
    0.42
     a
    0.41
     regulatory
    0.41
    Activations Density 0.004%

    No Known Activations