© 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. 154963
    Prev
    Next
    INDEX
    Explanations

    business, finance, and roles

    np_acts-logits-general · gemini-2.5-flash-lite

    Morphogenesis, traceability

    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
     нормально
    0.53
    𝐶
    0.52
    Ϩ
    0.51
    ڡ
    0.50
     яхшы
    0.48
     عادي
    0.48
    ј
    0.47
     eficiência
    0.47
     করছিলাম
    0.47
     μέσω
    0.47
    POSITIVE LOGITS
     meditating
    0.50
     metaverse
    0.48
     Mark
    0.48
     X
    0.47
     Senate
    0.46
     Arturo
    0.46
     XIX
    0.45
     Pollution
    0.45
     Ple
    0.44
     Chai
    0.43
    Activations Density 0.000%

    No Known Activations