© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    after determiners like the

    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
     "
    1.57
    “
    1.27
     “
    1.24
     God
    1.24
     '
    1.23
    -
    1.16
     „
    1.13
     also
    1.10
     «
    1.09
    *
    1.07
    POSITIVE LOGITS
    Фи
    1.54
    лась
    1.50
    ат
    1.45
     аль
    1.43
    фы
    1.42
     нор
    1.42
     دي
    1.42
    пред
    1.42
    сыпа
    1.42
     Ау
    1.41
    Activations Density 0.291%

    No Known Activations