© 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. 149418
    Prev
    Next
    INDEX
    Explanations

    activities and holidays

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

    explanations of terms

    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
    Subscribe
    0.46
    ko
    0.45
    klass
    0.45
    4
    0.44
     loyalty
    0.44
     )
    0.43
    ک
    0.43
    ge
    0.43
     magazine
    0.43
    نده
    0.43
    POSITIVE LOGITS
     Ос
    0.57
     възможно
    0.54
     וכ
    0.52
    rę
    0.52
     τότε
    0.51
     می‌شود
    0.50
     единица
    0.50
     راحت
    0.50
     ແລະ
    0.50
    にする
    0.48
    Activations Density 0.000%

    No Known Activations