© 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. 22-GEMMASCOPE-RES-131K
    7. 39009
    Prev
    Next
    INDEX
    Explanations

    numbers and divisions

    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_22/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
    itosti
    -0.84
    marché
    -0.84
    期望
    -0.80
     ploy
    -0.77
     addressee
    -0.76
     preva
    -0.76
    ジン
    -0.73
     ചെയ
    -0.73
     ancest
    -0.73
    Both
    -0.72
    POSITIVE LOGITS
     morning
    0.95
    datac
    0.93
    Dentro
    0.90
     subtypes
    0.89
    の中でも
    0.87
     further
    0.86
     ještě
    0.86
    ****/
    0.85
    пь
    0.85
    redge
    0.85
    Activations Density 0.130%

    No Known Activations