© 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. 3851
    Prev
    Next
    INDEX
    Explanations

    introduces summary

    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
    ,
    2.93
    .
    2.31
    -
    1.85
    (
    1.74
    ，
    1.70
    /
    1.64
    ،
    1.61
    、
    1.57
    ;
    1.55
    :
    1.44
    POSITIVE LOGITS
    During
    2.62
    According
    2.55
    Aside
    2.50
    Contrary
    2.49
     According
    2.42
     Согласно
    2.41
     zahlreichen
    2.40
    Following
    2.39
    上述
    2.38
     gemäß
    2.33
    Activations Density 0.285%

    No Known Activations