© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52067
    Prev
    Next
    INDEX
    Explanations

    font size specifications

    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
     Length
    0.52
     length
    0.50
    Length
    0.48
    长度
    0.48
    id
    0.47
     lengths
    0.47
     dài
    0.46
     n
    0.44
    orta
    0.43
     गरे
    0.42
    POSITIVE LOGITS
     inconsc
    0.44
    ലിയ
    0.42
     getopt
    0.41
     स्टोक्स
    0.41
    зов
    0.41
     pytanie
    0.41
    াগর
    0.40
     gloves
    0.40
     disposer
    0.40
     préférences
    0.39
    Activations Density 0.020%

    No Known Activations