© 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. 247282
    Prev
    Next
    INDEX
    Explanations

    sectors of, or other

    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
     hoteles
    0.48
     europ
    0.47
     vue
    0.44
     পেরিয়ে
    0.43
    ၡ
    0.43
     Andorra
    0.42
     ou
    0.42
     catering
    0.42
     garnis
    0.42
     أوروب
    0.42
    POSITIVE LOGITS
    ustum
    0.53
     verurs
    0.49
     այ
    0.48
    மே
    0.47
    ened
    0.46
    £
    0.45
    ৬
    0.45
    IZED
    0.44
    ARRANT
    0.44
    chyn
    0.44
    Activations Density 0.000%

    No Known Activations