© 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. 148366
    Prev
    Next
    INDEX
    Explanations

    becomes / worth / LA / URL

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

    quotes, to accomplish, thinking, lactose, Sign, López Obrador

    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
    มาร
    0.51
    সমস্ত
    0.46
     pu
    0.44
    說是
    0.44
    মাপ
    0.43
    ス
    0.43
    etype
    0.43
     older
    0.43
    തര
    0.42
    ernation
    0.42
    POSITIVE LOGITS
     संकट
    0.49
     मस्जिद
    0.49
    k
    0.49
     girişim
    0.47
     fundación
    0.46
     Cris
    0.46
     uygulam
    0.46
     आवेद
    0.46
     Kasım
    0.46
     Nghi
    0.46
    Activations Density 0.002%

    No Known Activations