© 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. 47141
    Prev
    Next
    INDEX
    Explanations

    phrases after common words

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

    listing events or items

    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
    展開
    0.49
    是一個
    0.47
    職
    0.47
    何
    0.46
    蒐
    0.46
    绿色
    0.45
    为了
    0.44
    事で
    0.44
    Naive
    0.44
    史上
    0.44
    POSITIVE LOGITS
     builtin
    0.49
     swims
    0.48
     inboard
    0.47
     אמ
    0.46
     tuba
    0.45
    :</
    0.45
    ..</
    0.45
     overpower
    0.44
     compensating
    0.44
     swim
    0.44
    Activations Density 0.000%

    No Known Activations