© 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. 34-GEMMASCOPE-RES-131K
    7. 31641
    Prev
    Next
    INDEX
    Explanations

    arrow-right or arrow width

    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_34/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
     muffin
    -0.79
    Gears
    -0.75
    ᅵ
    -0.75
     kili
    -0.74
    ícios
    -0.73
    spira
    -0.72
    tetten
    -0.69
    ⲁ
    -0.69
     полностью
    -0.69
     неизвест
    -0.69
    POSITIVE LOGITS
     Arrow
    1.13
     arrow
    0.85
     Courts
    0.82
    Arrow
    0.82
     Arrows
    0.79
     thinker
    0.78
     treated
    0.77
     tratados
    0.77
    individu
    0.76
     slant
    0.74
    Activations Density 0.009%

    No Known Activations