© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79563
    Prev
    Next
    INDEX
    Explanations

    definition or context

    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
     microcosm
    0.52
     重要
    0.47
    ਓ
    0.46
     attacc
    0.46
     migliorare
    0.45
    ೀರಿ
    0.45
     affrontare
    0.43
     شي
    0.43
     архі
    0.43
    <unused2016>
    0.43
    POSITIVE LOGITS
     being
    0.43
     as
    0.41
     answered
    0.41
    result
    0.39
    selecting
    0.39
     differing
    0.38
    json
    0.38
    वाहिक
    0.38
    ະລ
    0.38
     sonucu
    0.38
    Activations Density 0.010%

    No Known Activations