© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90047
    Prev
    Next
    INDEX
    Explanations

    clause or specific word

    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_31_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
    tail
    0.43
     G
    0.43
     T
    0.42
     traff
    0.41
     neur
    0.40
     torus
    0.39
     SPS
    0.39
    S
    0.39
     S
    0.39
     gr
    0.39
    POSITIVE LOGITS
     ако
    0.59
    т
    0.58
    หาก
    0.55
     если
    0.54
    यदि
    0.52
    إذا
    0.52
    ки
    0.52
    Если
    0.52
     إذا
    0.51
    き
    0.51
    Activations Density 0.001%

    No Known Activations