© 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. 202531
    Prev
    Next
    INDEX
    Explanations

    clinical signs or probability

    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
    ouna
    0.42
     alternativa
    0.42
    orn
    0.41
    izado
    0.41
    ored
    0.41
    пс
    0.41
    у
    0.41
    龙
    0.41
    이지만
    0.40
    ू
    0.40
    POSITIVE LOGITS
     peau
    0.52
    ･･･
    0.51
    ･･
    0.48
     የሆነ
    0.47
    ِيم
    0.47
    czech
    0.47
     रहस्य
    0.46
     reporter
    0.46
     condesc
    0.46
     delimited
    0.45
    Activations Density 0.001%

    No Known Activations