© 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. 25643
    Prev
    Next
    INDEX
    Explanations

    topics and descriptions

    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
     optimieren
    -0.96
    ࿚
    -0.94
     erwerben
    -0.93
     amorosa
    -0.92
     remonter
    -0.91
     ない
    -0.89
    ￢
    -0.89
     océano
    -0.88
    Харак
    -0.88
    ございます
    -0.87
    POSITIVE LOGITS
     and
    1.17
     because
    0.94
    薦
    0.93
    =====
    0.91
    okok
    0.91
    >>>>>
    0.89
     with
    0.87
    >>>>>>
    0.87
     while
    0.87
    ctory
    0.87
    Activations Density 0.105%

    No Known Activations