© 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. 24683
    Prev
    Next
    INDEX
    Explanations

    exclamations and emphasis

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

    numbered lists or calculations

    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
    த்தகைய
    0.54
    ЕВ
    0.48
    서울특별시
    0.48
    ஃப
    0.46
    ᴵ
    0.46
    REFERENCES
    0.45
    Título
    0.44
    ሥ
    0.44
    Iranian
    0.44
     τῶν
    0.43
    POSITIVE LOGITS
    !!!!
    0.63
     !!!!
    0.61
     VERY
    0.60
     very
    0.60
     gets
    0.58
    !!!!!
    0.58
     didn
    0.56
    ....
    0.55
    !!!
    0.55
     veggies
    0.54
    Activations Density 0.006%

    No Known Activations