© 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. 99782
    Prev
    Next
    INDEX
    Explanations

    Bank account or specific downloads

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

    will do, will use, will follow

    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
    şi
    0.51
     we
    0.46
     Umsatz
    0.45
    ggak
    0.45
     conosco
    0.44
     ẹ
    0.44
     o
    0.44
    și
    0.44
     apne
    0.44
     onerror
    0.44
    POSITIVE LOGITS
    钻
    0.44
     кислоты
    0.43
     বিপর্য
    0.43
     子供
    0.42
     அமிலம்
    0.42
     चिल्ड्रन
    0.42
     เศษ
    0.42
     Frederick
    0.41
     পিঁপ
    0.41
     চন্দ্র
    0.41
    Activations Density 0.001%

    No Known Activations