© 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. 1992
    Prev
    Next
    INDEX
    Explanations

    rate at which

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

    rate and speed

    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
     स्क
    0.43
     هفت
    0.42
    ㏄
    0.42
    ありますが
    0.42
     تعلیم
    0.41
    満足
    0.41
     jednej
    0.41
    citenamefont
    0.40
     فرد
    0.40
     peculiarities
    0.40
    POSITIVE LOGITS
     RATE
    0.55
    速率
    0.53
     Rate
    0.52
     pullover
    0.50
     agua
    0.50
    加快
    0.48
     rate
    0.47
    ㅄ
    0.44
     anymore
    0.43
     UPDATE
    0.43
    Activations Density 0.002%

    No Known Activations