© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70948
    Prev
    Next
    INDEX
    Explanations

    translated words and phrases

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

    exploring pros and cons with 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
    d
    0.44
    >
    0.44
    <0x93>
    0.43
    __________
    0.42
    药
    0.41
     can
    0.41
    子
    0.41
    can
    0.40
     ancest
    0.40
    球
    0.40
    POSITIVE LOGITS
    ॉक्स
    0.54
     sekret
    0.47
    ambuk
    0.47
     Sekret
    0.47
    venidos
    0.46
     détecter
    0.46
     hafta
    0.46
     ficam
    0.46
     abuso
    0.46
     découvre
    0.46
    Activations Density 0.001%

    No Known Activations