© 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. 49971
    Prev
    Next
    INDEX
    Explanations

    products images, your ideal, dual elig, always use

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

    traditional or modern approaches

    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
    ategorie
    0.46
    categorie
    0.45
     каждым
    0.45
    achtige
    0.43
     সবাইকে
    0.43
     всеми
    0.43
    樎
    0.43
    ত্রিম
    0.42
     hebben
    0.41
    本部
    0.41
    POSITIVE LOGITS
     .
    0.49
     sard
    0.49
    |.
    0.49
     intestine
    0.47
    PIRED
    0.44
     ⿻
    0.43
     infar
    0.43
     angina
    0.43
     لڑ
    0.42
    .
    0.42
    Activations Density 0.000%

    No Known Activations