© 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. 184816
    Prev
    Next
    INDEX
    Explanations

    California sales

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

    before using

    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
     e
    0.47
    ب
    0.46
     segments
    0.45
     değiştir
    0.45
    整体
    0.44
     and
    0.44
     aged
    0.42
     energía
    0.41
     simplesmente
    0.41
     ла
    0.40
    POSITIVE LOGITS
     ው
    0.50
    缪
    0.47
     يك
    0.47
    紬
    0.47
    伎
    0.46
     فائل
    0.46
     केले
    0.46
    URUK
    0.45
     حا
    0.45
    atir
    0.45
    Activations Density 0.001%

    No Known Activations