© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 45340
    Prev
    Next
    INDEX
    Explanations

    preparing for computations

    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
    the
    0.49
     correctional
    0.47
     classifying
    0.46
    挛
    0.46
    в
    0.45
     Correctional
    0.45
     वर्गीकृत
    0.44
    𝑉
    0.44
     למ
    0.43
     courtroom
    0.43
    POSITIVE LOGITS
     prepares
    0.52
     Preparing
    0.52
     préparations
    0.46
    準備
    0.44
     prepara
    0.43
     तैयारियां
    0.42
     подготовлено
    0.42
    alde
    0.41
     ripples
    0.40
     preparing
    0.40
    Activations Density 0.014%

    No Known Activations