© 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. 223905
    Prev
    Next
    INDEX
    Explanations

    words before specific completions

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

    keyword descriptions

    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
    6
    0.62
    7
    0.61
    9
    0.58
    8
    0.57
     subm
    0.51
    4
    0.49
     dd
    0.48
    5
    0.48
    !
    0.48
     angiogenic
    0.47
    POSITIVE LOGITS
     ponctuées
    0.46
    فوظ
    0.45
    ্যালি
    0.44
     veroor
    0.44
    eller
    0.43
    今後
    0.42
     причи
    0.42
    エリー
    0.41
    պ
    0.41
    вае
    0.41
    Activations Density 0.001%

    No Known Activations