© 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. 32364
    Prev
    Next
    INDEX
    Explanations

    platform, 64-bit, neutral

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

    platforms and operating systems

    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
    0.44
    hörigen
    0.43
    Tuple
    0.42
    RO
    0.42
    presumably
    0.41
    wd
    0.41
    imura
    0.41
    Pa
    0.41
    not
    0.40
    Eigen
    0.40
    POSITIVE LOGITS
     يا
    0.42
     प्रिंट
    0.41
    ੴ
    0.41
     airfoil
    0.40
     എന്നത്
    0.40
     पोजीशन
    0.40
     ऑस्ट्रेलिया
    0.39
     fanciful
    0.39
    AnyCPU
    0.39
    प्लेस
    0.38
    Activations Density 0.000%

    No Known Activations