© 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. 2798
    Prev
    Next
    INDEX
    Explanations

    cvsroot or isolated from

    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
     vroeger
    -0.79
     UO
    -0.74
     Fixtures
    -0.71
    uito
    -0.71
     brunt
    -0.70
    Svar
    -0.69
     eyelid
    -0.69
     urb
    -0.69
     vooraf
    -0.69
     imbal
    -0.68
    POSITIVE LOGITS
     NULL
    0.88
     zeigten
    0.88
     Whilst
    0.85
    Whilst
    0.84
     же
    0.83
    upon
    0.83
     totiž
    0.82
    kket
    0.81
     sł
    0.81
    dighet
    0.80
    Activations Density 0.001%

    No Known Activations