© 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. 132356
    Prev
    Next
    INDEX
    Explanations

    implemented well

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

    clarify a misunderstanding

    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
     themselves
    0.43
     iniz
    0.43
     સમા
    0.43
    Ꮈ
    0.42
    了几
    0.42
    寐
    0.42
    
    0.42
    们的
    0.41
     granddaughter
    0.40
     betreff
    0.40
    POSITIVE LOGITS
     よく
    0.50
    ется
    0.50
     कार्यकाल
    0.46
    method
    0.46
     एप्लिकेशन
    0.45
    бовать
    0.45
    aknya
    0.45
    лық
    0.44
    determination
    0.44
    лык
    0.43
    Activations Density 0.000%

    No Known Activations