© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 234865
    Prev
    Next
    INDEX
    Explanations

    company address

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     stemmed
    0.47
    setError
    0.47
    |$
    0.47
    сные
    0.45
    䛊
    0.45
    desIP
    0.45
     satisfactor
    0.45
     unserem
    0.45
     symbolizes
    0.45
    ΗΣ
    0.44
    POSITIVE LOGITS
    ش
    0.52
    n
    0.47
     rebuilding
    0.46
    the
    0.45
    ین
    0.44
    nst
    0.44
    론
    0.42
     وک
    0.42
     graphing
    0.41
    ш
    0.41
    Activations Density 0.000%

    No Known Activations