© 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. 55265
    Prev
    Next
    INDEX
    Explanations

    report recommendations and findings

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

    official investigations and recommendations

    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
     sparkly
    0.48
     অ্যাপ্লিকেশন
    0.46
     പുതു
    0.45
    協会
    0.42
     bragging
    0.41
     자동으로
    0.41
    သုံးပြု
    0.40
     长
    0.40
    会自动
    0.40
     Remover
    0.40
    POSITIVE LOGITS
     recommendations
    1.27
    Recommendations
    1.21
    recommend
    1.17
     Recommendations
    1.16
     report
    1.15
    report
    1.14
     Report
    1.10
    Report
    1.09
     recomendaciones
    1.08
     recommendation
    1.03
    Activations Density 0.091%

    No Known Activations