© 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. 245965
    Prev
    Next
    INDEX
    Explanations

    chandelier cleaning

    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
     monarch
    0.46
     كلمة
    0.46
    میری
    0.46
    ὄ
    0.45
    睚
    0.44
    ᱝ
    0.44
    結構
    0.43
     condivid
    0.43
    ວ່າ
    0.42
    рую
    0.41
    POSITIVE LOGITS
     buddhav
    0.49
     Eso
    0.46
     Reflections
    0.45
     aDAO
    0.45
     Ver
    0.44
     })();
    0.44
     Econom
    0.44
    esthetics
    0.44
     Buddhists
    0.44
     baos
    0.43
    Activations Density 0.001%

    No Known Activations