© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9390
    Prev
    Next
    INDEX
    Explanations

    probable future actions

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

    will not

    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_40_width_16k_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
    يكون
    0.51
     سيكون
    0.48
     ఉంటు
    0.44
     تكون
    0.43
     sarà
    0.43
     потребо
    0.43
     کان
    0.43
    能
    0.42
     থাকবে
    0.41
     legyen
    0.40
    POSITIVE LOGITS
     Often
    0.50
    often
    0.49
     parfois
    0.49
    往往
    0.46
     kadang
    0.46
     quelquefois
    0.45
    Often
    0.45
    铤
    0.44
    oughby
    0.44
     sometimes
    0.43
    Activations Density 0.279%

    No Known Activations