© 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. 137128
    Prev
    Next
    INDEX
    Explanations

    break down

    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
     bumpers
    0.45
    getMainUI
    0.44
    ulasi
    0.44
     butts
    0.44
    湳
    0.43
    ಲ್ಯ
    0.41
     senyawa
    0.41
    越し
    0.40
     cavité
    0.40
     lapisan
    0.39
    POSITIVE LOGITS
     below
    0.41
    iają
    0.39
    await
    0.39
     Israelites
    0.39
    enziale
    0.38
    Join
    0.37
     What
    0.37
    join
    0.37
    below
    0.35
    𝕥
    0.35
    Activations Density 0.001%

    No Known Activations