© 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. 70814
    Prev
    Next
    INDEX
    Explanations

    read ... reviews

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

    Unlike most, content following assets

    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
     ønsker
    0.50
    厅
    0.49
    ċ
    0.48
     anses
    0.47
     mindre
    0.46
     ambul
    0.43
     holders
    0.42
     ans
    0.42
     anteriormente
    0.42
     består
    0.41
    POSITIVE LOGITS
     выхода
    0.55
    ODBA
    0.49
    鴎
    0.47
     কবি
    0.47
    ութ
    0.47
    لقة
    0.46
     سعید
    0.45
     weit
    0.45
    ৪৩
    0.44
     بهره
    0.44
    Activations Density 0.000%

    No Known Activations