© 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-16K
    7. 1736
    Prev
    Next
    INDEX
    Explanations

    topics about

    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_16k_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
     orice
    1.35
     любого
    1.23
     ہزار
    1.21
     всички
    1.20
     любой
    1.17
     Многие
    1.16
     вдоль
    1.15
    經
    1.14
     qualunque
    1.14
     большинства
    1.13
    POSITIVE LOGITS
     sustainability
    2.28
     affordability
    2.25
     inclusivity
    2.23
     legality
    2.21
     topics
    2.16
     improving
    2.16
     regaining
    2.12
     getting
    2.10
     việc
    2.10
     prevention
    2.09
    Activations Density 0.873%

    No Known Activations