© 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. 32347
    Prev
    Next
    INDEX
    Explanations

    words to describe

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

    explaining, describing, beginning

    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
     unattended
    0.47
     ENVIRONMENTAL
    0.46
     EMERG
    0.43
     независимо
    0.42
     গঠনের
    0.41
     Glance
    0.40
    🚩
    0.40
    🆓
    0.40
     Synchron
    0.39
     Kxc
    0.39
    POSITIVE LOGITS
    无法
    0.84
    形容
    0.81
     Worte
    0.81
     describ
    0.74
     describir
    0.74
     describe
    0.73
     describing
    0.73
    describe
    0.73
     speechless
    0.73
    無法
    0.73
    Activations Density 0.075%

    No Known Activations