© 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. 26027
    Prev
    Next
    INDEX
    Explanations

    Phi Delta Theta Oklahoma

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

    related terms and context

    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
    کری
    0.46
     pokies
    0.44
     gott
    0.41
    の写真
    0.41
     kript
    0.41
    imb
    0.40
     snuff
    0.40
    ఠ
    0.40
    inhas
    0.40
    aino
    0.39
    POSITIVE LOGITS
    끊
    0.46
    \!
    0.40
     فکر
    0.40
    𝘧
    0.39
     தொடங்கிய
    0.39
    ClearedBy
    0.39
    사를
    0.38
    이를
    0.38
    유
    0.38
     nghĩ
    0.38
    Activations Density 0.000%

    No Known Activations