© 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. 5508
    Prev
    Next
    INDEX
    Explanations

    trembling

    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
    ‑
    1.90
     —
    1.78
    ‒
    1.67
    ...!
    1.67
     —,
    1.67
    ,—
    1.61
    !:
    1.58
     ―
    1.57
     –,
    1.56
    ‐
    1.51
    POSITIVE LOGITS
     yada
    2.37
    所以
    2.37
     alot
    2.23
    但是
    2.13
    "%
    2.12
    所以我
    2.10
    ”
    2.08
    “
    2.08
     sedangkan
    2.07
    那我們
    2.07
    Activations Density 0.229%

    No Known Activations