© 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. 203045
    Prev
    Next
    INDEX
    Explanations

    venture

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

    URLs and foreign scripts

    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
    忌
    0.48
     지역
    0.47
     以上
    0.47
     ethnicities
    0.46
     나가
    0.46
    Municipio
    0.45
    abdomen
    0.45
    jms
    0.45
     コン
    0.45
     cargos
    0.45
    POSITIVE LOGITS
    ور
    0.45
    ستر
    0.45
     ترب
    0.44
    ائدة
    0.43
     सुचेता
    0.43
     شده‌است
    0.43
    خ
    0.42
    र्ट
    0.42
     развед
    0.42
     драй
    0.42
    Activations Density 0.000%

    No Known Activations