© 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. 25862
    Prev
    Next
    INDEX
    Explanations

    legal cases and advocacy

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

    input_ids

    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
    O
    0.54
     jornal
    0.52
    '
    0.49
     ricev
    0.49
    ارو
    0.49
    GLOBALS
    0.48
    %
    0.48
    ).
    0.47
    /
    0.47
     street
    0.46
    POSITIVE LOGITS
     مطرح
    0.49
    Pics
    0.46
     күз
    0.42
     pics
    0.41
    ণ্ট
    0.41
     tzw
    0.41
     attacks
    0.41
    ন্ব
    0.41
     antagonist
    0.41
     achieves
    0.41
    Activations Density 0.000%

    No Known Activations