© 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. 58868
    Prev
    Next
    INDEX
    Explanations

    ain't gonna / ain't

    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
    ⢊
    -1.72
    sudadera
    -1.61
    ⢅
    -1.54
     acoso
    -1.49
    Pä
    -1.48
     всіх
    -1.47
    ij
    -1.46
    ėte
    -1.46
    :”
    -1.43
     compliant
    -1.41
    POSITIVE LOGITS
    嗐
    1.48
    er
    1.47
    ando
    1.46
    ba
    1.40
    at
    1.40
    os
    1.38
    l
    1.37
    y
    1.35
    is
    1.34
     whatnot
    1.34
    Activations Density 0.069%

    No Known Activations