© 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. 15295
    Prev
    Next
    INDEX
    Explanations

    new to a field or topic

    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
    ik
    0.49
     atheros
    0.47
    innov
    0.47
    ieni
    0.46
    ｙ
    0.46
    support
    0.46
    oward
    0.44
    private
    0.43
     поддержка
    0.42
     наиболее
    0.42
    POSITIVE LOGITS
     unfamiliar
    0.67
     intricacies
    0.57
     terminology
    0.56
     überhaupt
    0.48
    낯
    0.45
     helemaal
    0.44
     خیلی
    0.44
     coding
    0.44
     altogether
    0.43
    Terminology
    0.43
    Activations Density 0.054%

    No Known Activations