© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16438
    Prev
    Next
    INDEX
    Explanations

    special characters, punctuation, and short words

    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_65k_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
    건
    0.52
    ક્ત
    0.50
    ાર
    0.46
    мер
    0.46
    ન્ટ
    0.44
     tempt
    0.43
     બન
    0.43
    액
    0.43
    рат
    0.43
     projectId
    0.42
    POSITIVE LOGITS
    oja
    0.48
     Supporting
    0.47
    oltre
    0.47
    odeling
    0.46
    Value
    0.45
    uerte
    0.44
    ul
    0.44
    ould
    0.43
    uries
    0.43
    㥳
    0.42
    Activations Density 0.010%

    No Known Activations