© 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. 28285
    Prev
    Next
    INDEX
    Explanations

    heart faux pearls

    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
    shooter
    0.40
    tolerance
    0.39
     سفارش
    0.39
    =*
    0.39
    橡
    0.38
    aysa
    0.38
    dm
    0.38
    piegel
    0.38
    ensa
    0.37
    try
    0.37
    POSITIVE LOGITS
     cunt
    0.43
    漃
    0.40
    ляр
    0.39
     Canary
    0.39
     canary
    0.37
    aring
    0.35
    uge
    0.35
     Merci
    0.35
     когда
    0.35
    บริ
    0.35
    Activations Density 0.001%

    No Known Activations