© 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. 106082
    Prev
    Next
    INDEX
    Explanations

    future outcomes or consequences

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

    changing details, entities, bugs, selection

    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
    f
    0.50
    adc
    0.47
    faced
    0.47
    ោយ
    0.47
    varphi
    0.47
     інте
    0.46
    yson
    0.45
    white
    0.44
    stol
    0.44
    cup
    0.43
    POSITIVE LOGITS
    م
    0.49
    мб
    0.46
     خاط
    0.46
     بازدید
    0.45
    வான்
    0.43
    ลาคม
    0.43
    मिटेड
    0.43
    ugins
    0.42
     grinding
    0.42
    ያን
    0.42
    Activations Density 0.000%

    No Known Activations