© 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. 22-GEMMASCOPE-RES-131K
    7. 26179
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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_22/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
     miejsce
    -1.11
     compared
    -1.06
     (“
    -1.03
     to
    -1.01
     与
    -0.98
    んだから
    -0.97
    itons
    -0.96
     \%}$
    -0.96
     womit
    -0.96
     models
    -0.94
    POSITIVE LOGITS
    这个问题
    1.88
     answered
    1.43
     answer
    1.43
     asked
    1.39
     question
    1.30
     questions
    1.23
     Answered
    1.23
    Fragen
    1.19
     kysy
    1.16
    answered
    1.13
    Activations Density 0.049%

    No Known Activations