© 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. 79727
    Prev
    Next
    INDEX
    Explanations

    individual practitioners, vocal critics, practical advice

    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
    祺
    0.46
    越
    0.44
     viktigt
    0.44
    出血
    0.42
     فونبټ
    0.42
     میراتھن
    0.42
     complément
    0.42
     denominador
    0.41
     døde
    0.41
    崴
    0.41
    POSITIVE LOGITS
     Ска
    0.46
    डम
    0.44
     invites
    0.44
    কেন্ড
    0.44
    MB
    0.43
     dictates
    0.43
     Hab
    0.42
     tongue
    0.42
     इसको
    0.41
     invite
    0.41
    Activations Density 0.005%

    No Known Activations