© 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. 5720
    Prev
    Next
    INDEX
    Explanations

    titles and academic topics

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

    book titles and academic subjects

    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
    کومت
    0.46
     kttt
    0.39
    鹸
    0.38
    𒅅
    0.38
    樖
    0.38
    葢
    0.38
     famosos
    0.37
     फिल्में
    0.36
     एंज
    0.36
    Ⲓ
    0.36
    POSITIVE LOGITS
     -
    0.44
    0
    0.39
     his
    0.38
      
    0.36
    s
    0.36
     ,
    0.35
     their
    0.35
     to
    0.35
     not
    0.35
     because
    0.34
    Activations Density 0.000%

    No Known Activations