© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19568
    Prev
    Next
    INDEX
    Explanations

    calculus and fluid handling

    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
     CPUs
    0.55
    ئات
    0.51
     antiviral
    0.50
     низ
    0.46
    🥱
    0.43
    ার্থীরা
    0.43
     Viruses
    0.43
     Relaxation
    0.42
     Fittings
    0.42
    ائ
    0.42
    POSITIVE LOGITS
    工程
    0.46
    henderit
    0.46
    asmim
    0.44
     रत्न
    0.44
    agraph
    0.42
    modified
    0.41
     거짓
    0.40
    律
    0.40
     이름을
    0.40
    有问题
    0.40
    Activations Density 0.001%

    No Known Activations