© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1839
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Revision
    2.34
    佢
    2.27
     速
    2.21
     historians
    2.21
     disampaikan
    2.21
    她在
    2.20
     biographer
    2.16
    inist
    2.14
     Strategy
    2.13
    囝
    2.11
    POSITIVE LOGITS
    7
    3.41
    rinsic
    3.35
    6
    3.02
    8
    3.01
     irres
    2.71
     وبالتالي
    2.67
    ísk
    2.65
    이며
    2.65
     ponieważ
    2.63
    9
    2.62
    Activations Density 3.629%

    No Known Activations