© 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. 206505
    Prev
    Next
    INDEX
    Explanations

    physical attributes or legal agreements

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

    punctuation and structured 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
    ("",
    0.47
     defocus
    0.45
     وليس
    0.44
    containing
    0.44
    :"",
    0.44
    丟
    0.44
    getFullName
    0.43
    だが
    0.43
    thema
    0.43
    लेकिन
    0.42
    POSITIVE LOGITS
    নো
    0.48
    确保
    0.44
    镣
    0.43
     filament
    0.42
    始终
    0.39
    ր
    0.39
    一般来说
    0.39
     نمایند
    0.38
    éri
    0.38
    新生
    0.37
    Activations Density 0.002%

    No Known Activations