© 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-65K
    7. 3671
    Prev
    Next
    INDEX
    Explanations

    date ranges separated by slash or hyphen

    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
     oldCount
    0.22
    스가
    0.22
    സില്‍
    0.22
     tumorigen
    0.22
     leprosy
    0.22
     ด่า
    0.21
    ക്കാന്‍
    0.21
    婦
    0.20
    <unused1001>
    0.20
     murdered
    0.20
    POSITIVE LOGITS
     onwards
    0.40
     onward
    0.33
    +
    0.32
    /
    0.30
    乃至
    0.28
    -
    0.27
    –
    0.27
    hingga
    0.26
     hingga
    0.25
    inicio
    0.25
    Activations Density 0.126%

    No Known Activations