© 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. 8052
    Prev
    Next
    INDEX
    Explanations

    indicating cessation or impossibility

    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
     seb
    1.56
     Top
    1.50
     It
    1.46
     corresponding
    1.46
    '
    1.39
     current
    1.38
     G
    1.38
     A
    1.37
     Me
    1.36
     Select
    1.36
    POSITIVE LOGITS
    theless
    3.34
     봅시다
    2.32
    kgs
    2.32
    ppelin
    2.31
    ouilles
    2.31
    ocross
    2.31
    ıldı
    2.30
    CoO
    2.28
    eload
    2.26
    daa
    2.24
    Activations Density 0.053%

    No Known Activations