© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2496
    Prev
    Next
    INDEX
    Explanations

    artistic woman describing her

    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
     nombreux
    2.95
     nombreuses
    2.53
     adjournment
    2.51
     速
    2.42
     Trips
    2.40
     Vicar
    2.31
     Severn
    2.29
    年は
    2.27
    コツ
    2.25
     Announcements
    2.24
    POSITIVE LOGITS
    7
    3.45
    rinsic
    3.34
    8
    3.11
    6
    2.77
    enough
    2.73
    issimo
    2.67
    recv
    2.66
     enough
    2.64
    emptyset
    2.62
    5
    2.48
    Activations Density 0.875%

    No Known Activations