© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135298
    Prev
    Next
    INDEX
    Explanations

    certain taxpayers

    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
     компенса
    0.39
    讶
    0.39
    窍
    0.38
     capricious
    0.38
     Explosion
    0.37
     نحاول
    0.37
     auxilia
    0.37
     периоди
    0.37
     ક્ષ
    0.37
     evanes
    0.37
    POSITIVE LOGITS
    lid
    0.44
    falls
    0.43
    띠
    0.41
    insulated
    0.40
    scrap
    0.40
    produce
    0.39
    ляє
    0.39
    embra
    0.38
    substring
    0.38
    abra
    0.38
    Activations Density 0.000%

    No Known Activations