© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5293
    Prev
    Next
    INDEX
    Explanations

    wahrscheinlichkeit gilt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    hetiti
    2.62
    дами
    2.54
    <unused949>
    2.52
    okinetics
    2.51
    <unused933>
    2.47
    agory
    2.45
     做
    2.44
    occan
    2.44
    <unused946>
    2.42
    anoic
    2.41
    POSITIVE LOGITS
     beide
    2.97
     heute
    2.91
     auch
    2.91
     selbst
    2.91
     beiden
    2.90
     neue
    2.90
     andere
    2.88
     über
    2.87
     gehe
    2.86
     besonders
    2.83
    Activations Density 0.064%

    No Known Activations