© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 5031
    Prev
    Next
    INDEX
    Explanations

    start of a program

    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
    Negative Logits
    6
    1.43
    9
    1.28
    ⅜
    1.23
    ترك
    1.22
    ⅙
    1.22
    ">—
    1.21
    7
    1.20
     Miscellaneous
    1.19
     misuse
    1.19
     wre
    1.17
    POSITIVE LOGITS
     informs
    1.03
     πληροφο
    0.83
     garantizar
    0.82
     Ansari
    0.79
     confirms
    0.79
    Pro
    0.77
    erto
    0.75
     permet
    0.74
    し
    0.72
    pro
    0.72
    Activations Density 0.003%

    No Known Activations