© 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. 32396
    Prev
    Next
    INDEX
    Explanations

    larger compound nouns

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

    reviewer clearly states

    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
     テ
    0.36
     calcul
    0.34
     ನೀರಿನ
    0.34
     計算
    0.33
     ಮನೆ
    0.33
    筅
    0.33
     ಮನೆಯ
    0.33
     まず
    0.32
     dibujo
    0.32
    ố
    0.32
    POSITIVE LOGITS
    认为是
    0.47
    အား
    0.39
     comedic
    0.38
    说是
    0.38
     ["
    0.38
     swapped
    0.37
    女朋友
    0.37
     Insider
    0.37
    被称为
    0.36
    ständen
    0.36
    Activations Density 0.000%

    No Known Activations