© 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. 96918
    Prev
    Next
    INDEX
    Explanations

    game of halves

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

    relationships and examples

    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
     .
    0.49
     ters
    0.49
    cono
    0.48
    dam
    0.48
     tent
    0.47
     presidential
    0.46
     prefer
    0.46
     cocina
    0.45
     wrongfully
    0.45
     شی
    0.45
    POSITIVE LOGITS
    י
    0.55
    克
    0.54
    败
    0.49
    Moles
    0.49
    т
    0.49
    蝮
    0.48
    వ్య
    0.47
    २
    0.47
    ཾ
    0.47
    iotics
    0.47
    Activations Density 0.000%

    No Known Activations