© 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. 175775
    Prev
    Next
    INDEX
    Explanations

    call to action

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

    data processing

    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
     מספר
    0.55
     那麼
    0.48
    רי
    0.44
     }+\
    0.43
    eve
    0.43
    手術
    0.43
    ס
    0.43
    程度
    0.43
     povinn
    0.43
     זה
    0.42
    POSITIVE LOGITS
     inventions
    0.51
     élim
    0.44
     dials
    0.43
     già
    0.43
     îmb
    0.43
     Tess
    0.42
     concernant
    0.42
     faucets
    0.42
     articolo
    0.41
     έως
    0.41
    Activations Density 0.000%

    No Known Activations