© 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. 143186
    Prev
    Next
    INDEX
    Explanations

    anticipating and describing content

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

    introduces explanatory context or lists

    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
    ভিয়েতনাম
    0.54
    imą
    0.51
     događ
    0.49
    onaise
    0.49
    ಇದ
    0.48
     конкре
    0.48
    缓冲区
    0.47
     ":"
    0.47
    认证
    0.47
    সরকারি
    0.46
    POSITIVE LOGITS
     equilibr
    0.55
     superbe
    0.49
     نحل
    0.47
     seeming
    0.46
     ruthless
    0.45
     nonequilibrium
    0.45
     sophistic
    0.45
     aproxim
    0.43
     entusi
    0.43
     ethereal
    0.42
    Activations Density 0.000%

    No Known Activations