© 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. 15-GEMMASCOPE-2-RES-16K
    7. 6072
    Prev
    Next
    INDEX
    Explanations

    working with

    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_15_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
     hydrant
    1.08
     mtu
    0.98
     awali
    0.93
    抜き
    0.93
    コマ
    0.92
     RACE
    0.91
     <?=
    0.89
    かわらず
    0.88
    писание
    0.88
     снять
    0.88
    POSITIVE LOGITS
    "，
    1.43
    onas
    1.40
    Magn
    1.36
    as
    1.35
    ful
    1.35
     Magn
    1.33
    <>();
    1.33
     şekilde
    1.33
    的看着
    1.33
     fans
    1.32
    Activations Density 0.122%

    No Known Activations