© 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. 16357
    Prev
    Next
    INDEX
    Explanations

    day or period indicators

    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
    gameOver
    0.44
    ങ
    0.43
     розу
    0.42
    hető
    0.42
    হতের
    0.41
    ROE
    0.41
    Yok
    0.41
    鹰
    0.40
    amis
    0.40
     ब्राउ
    0.40
    POSITIVE LOGITS
     Telugu
    0.54
     schoolchildren
    0.52
     evening
    0.50
     Morning
    0.50
     Bengali
    0.49
     diurnal
    0.48
     Malayalam
    0.48
     Afternoon
    0.47
     Night
    0.47
     অনুষ্ঠানের
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.