© 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. 201408
    Prev
    Next
    INDEX
    Explanations

    output format is json

    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
     be
    0.52
    柄
    0.45
    كيف
    0.42
     keinen
    0.42
     botão
    0.42
    Ave
    0.41
     seinen
    0.40
     জন
    0.39
    ｏ
    0.39
     keine
    0.39
    POSITIVE LOGITS
     afirm
    0.44
    ̉
    0.43
     goodies
    0.42
     Shirts
    0.42
     manifesto
    0.41
     liberalization
    0.40
     mixture
    0.40
     reactions
    0.40
     afterPath
    0.40
     Lordships
    0.40
    Activations Density 0.008%

    No Known Activations