© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134361
    Prev
    Next
    INDEX
    Explanations

    blending science, one, blizzard decades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     congen
    0.41
    0.40
    bigcap
    0.38
    ගේ
    0.37
     subspecies
    0.37
     معم
    0.36
     arquitect
    0.36
    ":{"
    0.35
     Subsec
    0.34
     nicht
    0.34
    POSITIVE LOGITS
    뷁
    0.38
     Swann
    0.38
    Lengths
    0.37
    鸹
    0.37
    नौ
    0.36
    ™.
    0.36
     सिलसिले
    0.36
    Adopt
    0.36
    awara
    0.36
    惚
    0.35
    Activations Density 0.001%

    No Known Activations