© 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. 260547
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     отсутствие
    0.54
     tratamento
    0.50
    '`,
    0.49
     এখনও
    0.48
     এখনো
    0.46
     disponibilidade
    0.45
    amination
    0.45
    ຄວ
    0.45
     école
    0.45
     PFAS
    0.45
    POSITIVE LOGITS
     Profesional
    0.46
    ثال
    0.45
    خته
    0.44
     hennes
    0.44
     femin
    0.43
    放下
    0.43
     gyne
    0.43
    펙
    0.43
    出来ます
    0.42
    ण्ड
    0.42
    Activations Density 0.000%

    No Known Activations