© 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. 209128
    Prev
    Next
    INDEX
    Explanations

    credit decisions, weddings

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

    accidental, visually, large, Chinese, reliant, more

    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
    الد
    0.48
    قيقي
    0.47
    趼
    0.47
    гова
    0.46
    珹
    0.45
    בש
    0.45
    போது
    0.44
    Ｅ
    0.44
    拶
    0.44
    繧
    0.43
    POSITIVE LOGITS
     tör
    0.46
     পরস্পর
    0.46
     tartan
    0.44
    isjon
    0.43
     l
    0.43
    ian
    0.41
    ottak
    0.41
     principales
    0.40
     errand
    0.40
    out
    0.40
    Activations Density 0.001%

    No Known Activations