© 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. 3446
    Prev
    Next
    INDEX
    Explanations

    blue whale

    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
     storyteller
    1.50
     biographer
    1.44
    FontSize
    1.43
     ziehen
    1.43
    Solver
    1.40
    페이스
    1.37
     yorum
    1.35
    芡
    1.34
    akukannya
    1.33
    龈
    1.31
    POSITIVE LOGITS
     items
    3.66
    items
    3.50
     Items
    3.24
    Items
    3.19
     goods
    3.16
     itens
    2.94
     ITEMS
    2.85
     belongings
    2.80
     materials
    2.79
    物品
    2.78
    Activations Density 0.944%

    No Known Activations