© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178177
    Prev
    Next
    INDEX
    Explanations

    a verb following common words

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

    impact and significance

    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
    比如
    0.52
    țiile
    0.51
    end
    0.50
    encer
    0.50
    例如
    0.49
            
    0.48
    encias
    0.48
    Inicial
    0.48
    值
    0.48
    alte
    0.47
    POSITIVE LOGITS
    NASDAQ
    0.46
     روشنی
    0.46
     अपेक्षा
    0.46
     преимуще
    0.43
     書い
    0.42
     medan
    0.42
     kring
    0.42
     कर्नाटक
    0.42
     joyous
    0.42
    穰
    0.41
    Activations Density 0.000%

    No Known Activations