© 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. 67088
    Prev
    Next
    INDEX
    Explanations

    RenWeb, cleaning, data recovery

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

    key features and themes

    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
    r
    0.47
     člán
    0.46
     bo
    0.45
    ન્મ
    0.45
    rage
    0.45
    थ
    0.45
    ंध
    0.44
    椛
    0.44
    眾
    0.44
    κι
    0.43
    POSITIVE LOGITS
    栾
    0.46
     السيارات
    0.46
    BeanFactory
    0.44
     Palabra
    0.44
    afio
    0.44
     Gerrard
    0.43
     ceremon
    0.43
     कुर्सी
    0.43
    urup
    0.42
     Gaj
    0.41
    Activations Density 0.001%

    No Known Activations