© 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. 126146
    Prev
    Next
    INDEX
    Explanations

    years, deficits, bracket, cut, pocket

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

    language, etfs

    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
    М
    0.54
    А
    0.52
    ОВ
    0.49
    8
    0.49
    У
    0.49
    Ки
    0.48
    Ин
    0.47
    К
    0.47
    Ц
    0.47
    Ф
    0.47
    POSITIVE LOGITS
     encanta
    0.58
     had
    0.56
     hates
    0.56
     was
    0.55
     didn
    0.55
     hiçbir
    0.54
     wasn
    0.54
     nemmeno
    0.53
     bukanlah
    0.53
     estuvo
    0.52
    Activations Density 0.001%

    No Known Activations