© 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. 127016
    Prev
    Next
    INDEX
    Explanations

    both medical and military

    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
    죽
    0.45
    НЫ
    0.45
    蛎
    0.45
     Einwohner
    0.44
    ković
    0.44
     xScale
    0.44
    lső
    0.44
     VALUE
    0.44
     DESCRIPTION
    0.43
     FORMAT
    0.42
    POSITIVE LOGITS
    a
    0.49
     glared
    0.48
    Ang
    0.47
    Energ
    0.45
     благо
    0.45
    Raven
    0.44
     alegría
    0.44
    Blend
    0.44
    年輕
    0.44
    Pig
    0.43
    Activations Density 0.002%

    No Known Activations