© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3387
    Prev
    Next
    INDEX
    Explanations

    index of / on Bay

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     वाला
    2.71
    ッシュ
    2.43
    ム
    2.33
    dated
    2.30
    OUS
    2.28
     Tipp
    2.26
     arrows
    2.25
    ポン
    2.24
    姆
    2.24
     announcements
    2.23
    POSITIVE LOGITS
    6
    1.81
    7
    1.67
    8
    1.60
    竞争力
    1.51
    4
    1.39
     coexist
    1.39
    9
    1.29
    需求的
    1.29
    3
    1.29
     continuamente
    1.28
    Activations Density 0.182%

    No Known Activations