© 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. 8872
    Prev
    Next
    INDEX
    Explanations

    code structure and punctuation

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

    ** ` [ ] { } `

    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
    鱉
    0.48
    StarGo
    0.46
    çou
    0.44
    鹌
    0.44
    getStudentNo
    0.44
     цилинд
    0.44
    罍
    0.43
    ꧁
    0.43
    鎏
    0.43
     svært
    0.42
    POSITIVE LOGITS
    s
    0.71
    ;
    0.61
    ,
    0.47
    dle
    0.47
    d
    0.46
    nums
    0.45
    n
    0.44
    oscopes
    0.44
    ፤
    0.44
     accuracies
    0.44
    Activations Density 0.005%

    No Known Activations