© 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. 32114
    Prev
    Next
    INDEX
    Explanations

    items separated by delimiters

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

    splitting strings by delimiter

    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
    消除
    0.57
    eval
    0.54
    or
    0.50
    func
    0.48
    perf
    0.48
     or
    0.47
    移除
    0.46
    a
    0.46
    oran
    0.45
    el
    0.45
    POSITIVE LOGITS
     লিখিয়াছেন
    0.47
    ছিলাম
    0.44
     riječi
    0.44
    炜
    0.43
     einzig
    0.43
     razlik
    0.43
     autochtones
    0.42
    煒
    0.42
     Вай
    0.42
     limites
    0.42
    Activations Density 0.001%

    No Known Activations