© 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. 99242
    Prev
    Next
    INDEX
    Explanations

    purpose or requirement

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

    ChatGPT is a closed-source model

    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
    せん
    0.47
    нных
    0.45
    zäh
    0.45
    렙
    0.45
     Besuch
    0.45
     strán
    0.44
    西哥
    0.44
    שׁ
    0.43
    娌
    0.42
    ěst
    0.42
    POSITIVE LOGITS
     دو
    0.52
     upholding
    0.48
     iki
    0.47
     عاشق
    0.47
     subsidies
    0.47
     повышен
    0.45
     syringes
    0.45
     kidneys
    0.44
    ুগত্য
    0.44
     antidepressants
    0.44
    Activations Density 0.001%

    No Known Activations