© 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. 246344
    Prev
    Next
    INDEX
    Explanations

    saving by tax reform

    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
     capacidades
    0.53
     capacities
    0.47
    entered
    0.46
     작업을
    0.46
     لیون
    0.46
     вина
    0.45
     니
    0.45
     написа
    0.45
     пода
    0.45
    uch
    0.44
    POSITIVE LOGITS
    遵循
    0.52
    杓
    0.52
    曩
    0.52
    不断
    0.51
    ী
    0.50
    妫
    0.50
    ាញ
    0.49
     récente
    0.49
    不斷
    0.49
    拶
    0.49
    Activations Density 0.001%

    No Known Activations