© 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. 57916
    Prev
    Next
    INDEX
    Explanations

    ans, ansel, ansatz

    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
     avenge
    -0.73
    不做
    -0.71
    íteni
    -0.71
    Acrylic
    -0.71
     Rick
    -0.71
    际
    -0.70
     equip
    -0.69
    딴
    -0.69
    iked
    -0.68
    폴
    -0.68
    POSITIVE LOGITS
     Ans
    0.84
     Schie
    0.83
     Ansel
    0.82
     forcément
    0.81
    bile
    0.81
     Lumière
    0.80
    atasi
    0.78
    Ans
    0.78
     ans
    0.77
     Fonds
    0.76
    Activations Density 0.019%

    No Known Activations