© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40507
    Prev
    Next
    INDEX
    Explanations

    summary >

    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
    enerys
    -1.84
     如果
    -1.80
    derdag
    -1.73
     Obtén
    -1.71
    rollen
    -1.70
    seperti
    -1.70
    menjadi
    -1.68
    ')";
    -1.68
    archiwizowane
    -1.65
     Vereinig
    -1.63
    POSITIVE LOGITS
     they
    2.06
    :
    1.89
     really
    1.74
     always
    1.68
    ↵
    1.57
     still
    1.56
     not
    1.55
    "
    1.52
     a
    1.51
     very
    1.49
    Activations Density 0.001%

    No Known Activations