© 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. 48249
    Prev
    Next
    INDEX
    Explanations

    data array info

    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
    </h2>
    0.71
    I
    0.64
    </h1>
    0.64
    Step
    0.62
    汙
    0.60
    Flight
    0.58
     fait
    0.57
     ذخ
    0.57
    Der
    0.55
     आखिरी
    0.55
    POSITIVE LOGITS
    y
    0.60
    тельность
    0.58
    gruppen
    0.57
    gados
    0.55
    yama
    0.55
     দলে
    0.54
    kül
    0.53
    yta
    0.52
    листи
    0.52
    쨩
    0.51
    Activations Density 0.001%

    No Known Activations