© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67699
    Prev
    Next
    INDEX
    Explanations

    Ansatz and related German endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    and
    -3.14
    but
    -2.31
     但
    -2.20
     οπο
    -2.20
    ’，
    -1.99
     He
    -1.98
    姈
    -1.96
    但
    -1.82
    是
    -1.77
    If
    -1.77
    POSITIVE LOGITS
    跸
    2.30
    ஂ
    2.17
    abinieri
    2.09
    洐
    2.06
    Ꞓ
    2.05
     самая
    2.03
    哢
    2.00
    s
    2.00
    ásica
    1.95
    杙
    1.91
    Activations Density 0.002%

    No Known Activations