© 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. 1420
    Prev
    Next
    INDEX
    Explanations

    times and periods

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

    time ranges and periods

    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
     దాని
    0.34
     assass
    0.31
     errone
    0.31
    錯誤
    0.30
    })^
    0.29
    اتھن
    0.29
    <unused44>
    0.28
    േഷന്‍
    0.28
    疑問
    0.27
    鈉
    0.27
    POSITIVE LOGITS
    -
    0.37
     -
    0.35
    est
    0.33
    oc
    0.33
    ong
    0.33
     University
    0.32
    ay
    0.32
     days
    0.32
     until
    0.32
    ov
    0.32
    Activations Density 0.182%

    No Known Activations