© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    even if

    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
    '
    1.85
    \
    1.47
     prostu
    1.45
    ische
    1.38
    a
    1.36
     rač
    1.32
    :
    1.31
    ’
    1.30
    "
    1.28
    [
    1.24
    POSITIVE LOGITS
     though
    2.20
    handedly
    1.90
    entimes
    1.82
     несмотря
    1.78
     worse
    1.75
     overshadow
    1.73
    ificant
    1.69
     если
    1.68
     ffilm
    1.67
    greens
    1.67
    Activations Density 0.123%

    No Known Activations