© 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. 88096
    Prev
    Next
    INDEX
    Explanations

    miss out on this

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

    miss out

    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
    ┍
    0.47
     रखेंगे
    0.44
    ђено
    0.44
    મિંગ
    0.44
    ليك
    0.43
    рован
    0.43
    Итак
    0.41
    热情
    0.41
    تبقى
    0.41
    脱
    0.41
    POSITIVE LOGITS
     this
    0.52
     diesem
    0.50
     -
    0.47
     এই
    0.46
     இவ்வ
    0.46
     هذا
    0.46
     這個
    0.45
     This
    0.44
     گر
    0.43
     schop
    0.43
    Activations Density 0.010%

    No Known Activations