© 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. 3877
    Prev
    Next
    INDEX
    Explanations

    file name or path

    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
    ))>
    1.35
     scorpion
    1.34
    度は
    1.27
     final
    1.26
    onacci
    1.23
     rosemary
    1.21
     sanitary
    1.20
     signatures
    1.19
     extra
    1.17
    )]=
    1.17
    POSITIVE LOGITS
    owę
    1.60
     ولا
    1.57
     Казахстан
    1.49
    iracial
    1.45
    จีน
    1.40
    eryka
    1.37
    ovod
    1.36
    hq
    1.33
    байд
    1.33
    attrib
    1.32
    Activations Density 0.000%

    No Known Activations