© 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. 5752
    Prev
    Next
    INDEX
    Explanations

    your understanding

    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
     uzys
    1.34
     maksymal
    1.28
    Ę
    1.27
     umo
    1.24
     +,
    1.23
    Aden
    1.20
     OFFICE
    1.20
    +</
    1.19
     qo
    1.18
     dili
    1.18
    POSITIVE LOGITS
     part
    1.25
    Part
    1.13
    part
    1.11
     parts
    1.08
    parts
    1.07
    portion
    1.03
    wif
    0.98
    續
    0.98
    ism
    0.98
    ัญลักษณ์
    0.97
    Activations Density 0.064%

    No Known Activations