© 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. 71976
    Prev
    Next
    INDEX
    Explanations

    i7 processors

    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
     전자
    0.53
    ७
    0.47
     elektron
    0.46
     대상
    0.45
     ইলেক্ট
    0.45
    știg
    0.45
    ዀ
    0.45
    冚
    0.44
    deployRoot
    0.43
    𝚗
    0.43
    POSITIVE LOGITS
     Monochrome
    0.48
    r
    0.48
     monoc
    0.46
     دیدار
    0.44
     договор
    0.44
     oa
    0.44
     Monroe
    0.44
    w
    0.44
     Neymar
    0.43
     w
    0.42
    Activations Density 0.009%

    No Known Activations