© 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. 22278
    Prev
    Next
    INDEX
    Explanations

    creation of academic and creative works

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

    synthetically generated content and features

    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
    BlackRatingDiff
    0.44
    ৯
    0.40
    IsMethod
    0.40
    seekers
    0.39
    proble
    0.38
    <unused2>
    0.38
    paced
    0.38
     機能
    0.38
    ாது
    0.38
    ៦
    0.38
    POSITIVE LOGITS
     |
    0.53
      
    0.45
     Campus
    0.42
     của
    0.42
     […]
    0.41
     Essay
    0.41
     Undergraduate
    0.41
     Login
    0.40
       
    0.40
     Creative
    0.40
    Activations Density 0.034%

    No Known Activations