© 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. 181458
    Prev
    Next
    INDEX
    Explanations

    artisans multiplying separation

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

    online or offline navigation

    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
    lega
    0.47
    port
    0.47
    ħ
    0.46
     situations
    0.46
    可能會
    0.46
     Environment
    0.46
    d
    0.45
                                   
    0.44
     Packaging
    0.44
    新鮮
    0.44
    POSITIVE LOGITS
     Тех
    0.55
     последних
    0.50
     Мне
    0.49
    ͢
    0.48
    멤
    0.48
     스토리
    0.47
     продол
    0.47
     dissociated
    0.46
     интегри
    0.46
     xổ
    0.45
    Activations Density 0.000%

    No Known Activations