© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92677
    Prev
    Next
    INDEX
    Explanations

    specific bracketed text

    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
     डिप्ट
    0.48
    UARY
    0.46
     HOWEVER
    0.46
     ಅವರು
    0.45
    ᴰ
    0.45
    ండి
    0.44
     Unisex
    0.44
    🥭
    0.44
    BUT
    0.44
     காட்டு
    0.44
    POSITIVE LOGITS
     place
    0.50
     lugar
    0.50
    كمل
    0.45
    ^{\
    0.45
    uchs
    0.44
    ピ
    0.44
    の名
    0.43
    ema
    0.43
    ime
    0.42
     unaccount
    0.42
    Activations Density 0.004%

    No Known Activations