© 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. 203317
    Prev
    Next
    INDEX
    Explanations

    spiritual teacher

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

    learning specific phrases

    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
    arlar
    0.52
    larınız
    0.52
    anı
    0.49
    الب
    0.49
    ்ப்ப
    0.48
    currentTime
    0.47
    ikleri
    0.47
    무
    0.47
    rasz
    0.47
    婳
    0.47
    POSITIVE LOGITS
     TMZ
    0.50
     degenerative
    0.48
     glomerul
    0.48
     anointed
    0.48
     WB
    0.47
     alcoholism
    0.47
     taxa
    0.47
     Fontainebleau
    0.47
     grandiose
    0.47
     متنوع
    0.46
    Activations Density 0.000%

    No Known Activations