© 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. 224229
    Prev
    Next
    INDEX
    Explanations

    weekend sales and job market

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

    validating or connecting devices

    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
    able
    0.49
     rainy
    0.48
     hydrolysis
    0.45
    -
    0.45
     hydrolyzed
    0.44
     hydros
    0.43
    р
    0.43
     rains
    0.43
    во
    0.43
     viewport
    0.43
    POSITIVE LOGITS
     તેને
    0.53
     teorías
    0.52
     teorie
    0.51
    صميم
    0.50
    𝒐
    0.50
     regole
    0.49
     તેમાં
    0.49
    ઉસ
    0.49
     アクセ
    0.49
    φέρει
    0.48
    Activations Density 0.000%

    No Known Activations