© 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. 225438
    Prev
    Next
    INDEX
    Explanations

    contrast and comparison

    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
     ولكن
    0.38
     voire
    0.37
    也将
    0.36
    ྛ
    0.35
    ものの
    0.34
    лік
    0.34
    并将
    0.34
     mutta
    0.34
     Including
    0.33
    َوْ
    0.33
    POSITIVE LOGITS
     unlike
    0.93
    unlike
    0.90
    Unlike
    0.79
     Unlike
    0.78
    不像
    0.75
     contrairement
    0.67
    there
    0.55
    相比
    0.54
     compared
    0.52
    compared
    0.52
    Activations Density 0.024%

    No Known Activations