© 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. 7363
    Prev
    Next
    INDEX
    Explanations

    version control

    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
    ỡi
    1.61
    賃
    1.50
    放題
    1.49
    あえず
    1.47
    zení
    1.45
    går
    1.43
     halus
    1.43
    ractors
    1.41
    ermak
    1.40
    ように
    1.35
    POSITIVE LOGITS
    гр
    2.64
    сом
    2.53
     flav
    2.37
    溯
    2.36
    но
    2.35
    َد
    2.29
    ωσε
    2.29
    до
    2.26
    н
    2.24
     puzz
    2.23
    Activations Density 0.009%

    No Known Activations