© 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. 166369
    Prev
    Next
    INDEX
    Explanations

    (date)

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

    separate entities or 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
     работа
    0.51
    Dairy
    0.49
    家长
    0.44
    WART
    0.43
    Commercial
    0.42
     DAIRY
    0.42
    efficacy
    0.42
    家
    0.41
    عمل
    0.41
    Evaluation
    0.40
    POSITIVE LOGITS
     posiada
    0.49
    aço
    0.48
    頤
    0.47
     derivada
    0.47
     있던
    0.47
     sulit
    0.44
     Semua
    0.43
    န်
    0.43
     Temmuz
    0.43
     memb
    0.42
    Activations Density 0.001%

    No Known Activations