© 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. 211069
    Prev
    Next
    INDEX
    Explanations

    concluding or separating phrases

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

    apostrophe cms, prophet forecasting, or noise

    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
     заработной
    0.54
     కొంత
    0.52
     употре
    0.52
     为
    0.50
     lua
    0.50
     ပြော
    0.49
     অপরিচিত
    0.48
     használ
    0.48
     podido
    0.48
    adó
    0.47
    POSITIVE LOGITS
    دی
    0.46
    鉄
    0.44
    同時に
    0.43
    ちゃんと
    0.43
    までの
    0.42
     سلسلے
    0.42
    걔
    0.42
    northern
    0.41
    一つ
    0.41
    reti
    0.41
    Activations Density 0.001%

    No Known Activations