© 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. 40-GEMMASCOPE-2-RES-262K
    7. 35414
    Prev
    Next
    INDEX
    Explanations

    baselines, basal, basilar, Basque, BASICS

    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_40_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
    និច
    0.43
     নীল
    0.41
     നീ
    0.40
    BLUE
    0.39
    cyan
    0.39
    舖
    0.39
    oui
    0.38
    Nic
    0.37
    plots
    0.37
    莒
    0.37
    POSITIVE LOGITS
    Bas
    0.43
     Bas
    0.42
     так
    0.42
     bas
    0.41
     worlds
    0.41
     கட்டு
    0.39
     faces
    0.39
     projected
    0.39
     baseline
    0.39
    способ
    0.39
    Activations Density 0.000%

    No Known Activations