© 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. 82651
    Prev
    Next
    INDEX
    Explanations

    symbols and emojis

    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
     hoà
    0.44
     popolare
    0.42
    ینده
    0.42
     hiper
    0.42
     عین
    0.42
    螯
    0.42
    㖑
    0.41
    ذیر
    0.41
     modalidad
    0.41
    inescence
    0.40
    POSITIVE LOGITS
    4
    0.53
    ят
    0.50
    5
    0.49
    بيت
    0.49
     періо
    0.48
    的
    0.48
    미
    0.47
    Від
    0.47
    ৪৭
    0.44
    Ге
    0.44
    Activations Density 0.001%

    No Known Activations