© 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. 67055
    Prev
    Next
    INDEX
    Explanations

    blog, feature, locals, SSO

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

    electrical systems and frameworks

    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
    我们
    0.48
    យើង
    0.48
    oteric
    0.48
     behöver
    0.46
    Наша
    0.45
     arka
    0.43
    අ
    0.43
    我們
    0.43
     Emerg
    0.42
     Nus
    0.42
    POSITIVE LOGITS
    י
    0.49
    desk
    0.46
    setRequest
    0.46
    ázky
    0.46
    ി
    0.45
    ılığı
    0.45
     스토리
    0.45
    destination
    0.44
    䂘
    0.44
    timevals
    0.44
    Activations Density 0.000%

    No Known Activations