© 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. 10-GEMMASCOPE-RES-131K
    7. 128999
    Prev
    Next
    INDEX
    Explanations

    began, STILL, AGAIN

    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_10/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
     specifically
    -1.61
    specifically
    -1.59
     budete
    -1.59
     zejména
    -1.57
    kız
    -1.56
     olisi
    -1.51
     に関する
    -1.49
     particolarmente
    -1.48
     estremamente
    -1.46
    erobic
    -1.45
    POSITIVE LOGITS
    ३
    1.70
    ५
    1.56
     from
    1.45
    ଷ
    1.41
     која
    1.41
     AGAIN
    1.38
    ｐ
    1.38
     began
    1.35
    шње
    1.34
     STILL
    1.33
    Activations Density 0.036%

    No Known Activations