© 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. 223390
    Prev
    Next
    INDEX
    Explanations

    numbers or categories

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

    specific noun 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
     বিবাহ
    0.48
     ሜ
    0.46
    ভেন
    0.46
     শিব
    0.44
    grounds
    0.44
    yst
    0.44
    splits
    0.43
     वाटर
    0.43
    喜欢的
    0.43
     তুরস্ক
    0.42
    POSITIVE LOGITS
    3
    0.52
    :
    0.49
    количество
    0.48
     incógn
    0.48
     enforced
    0.46
    程度の
    0.46
    -
    0.45
     occupants
    0.45
     interrogation
    0.44
     inaugur
    0.43
    Activations Density 0.000%

    No Known Activations