© 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. 2526
    Prev
    Next
    INDEX
    Explanations

    Roman numeral III section headings

    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
    snapshot
    1.73
    hashtag
    1.65
     Fei
    1.63
    ubarb
    1.60
    Translate
    1.53
    뻥
    1.52
    Snap
    1.52
    :@
    1.51
    Cheng
    1.51
     gyro
    1.51
    POSITIVE LOGITS
    II
    2.95
     II
    2.93
     III
    2.92
    III
    2.81
    ii
    2.54
     IV
    2.54
     VII
    2.43
     VIII
    2.33
    VII
    2.33
    iii
    2.29
    Activations Density 0.149%

    No Known Activations