© 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. 81277
    Prev
    Next
    INDEX
    Explanations

    conditional beginnings

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

    conditional phrases

    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
    from
    0.54
    0
    0.47
    ｓ
    0.46
    Airport
    0.45
    ze
    0.44
    ％
    0.44
    evi
    0.44
    4
    0.44
    letter
    0.43
    ската
    0.43
    POSITIVE LOGITS
     Jeżeli
    0.49
     Tâm
    0.48
     समाचार
    0.47
     اگر
    0.46
     Якщо
    0.44
     Wenn
    0.43
     Nếu
    0.43
     إذا
    0.43
    اگر
    0.43
     Earlier
    0.43
    Activations Density 0.000%

    No Known Activations