© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7975
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yled
    1.12
    0
    1.11
    izen
    1.09
    isen
    1.09
    udh
    1.05
    ause
    1.05
    ized
    1.00
    mla
    0.99
    jour
    0.94
    aner
    0.92
    POSITIVE LOGITS
     spindles
    2.18
     靴
    2.05
     Crypt
    2.05
     wink
    2.04
     Bunn
    2.00
    搔
    1.99
     chapel
    1.98
     פי
    1.98
     Jewellery
    1.98
    靴
    1.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.