© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11532
    Prev
    Next
    INDEX
    Explanations

    state management or machine

    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_16k_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
    ي
    0.93
    ת
    0.93
    ва
    0.78
    هاي
    0.69
    то
    0.68
    在
    0.67
    ير
    0.66
    يي
    0.65
    也
    0.65
    ين
    0.64
    POSITIVE LOGITS
     state
    1.26
     State
    1.13
    newState
    1.13
     राज्य
    1.07
     getState
    1.04
    Estado
    1.02
    State
    1.02
    state
    1.02
     상태
    1.01
     STATE
    0.99
    Activations Density 0.088%

    No Known Activations