© 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. 27315
    Prev
    Next
    INDEX
    Explanations

    code comments and structures

    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
    一旁的
    -1.02
    ッケージ
    -0.97
     опубликова
    -0.95
    ihnach
    -0.94
    UNDA
    -0.94
    ᆺ
    -0.93
    CREATE
    -0.92
     maintenant
    -0.92
     evidente
    -0.92
    leece
    -0.91
    POSITIVE LOGITS
     which
    1.32
     when
    1.21
    各种
    1.19
    imbangan
    1.19
     many
    1.18
    次代
    1.09
    了过去
    1.09
     variados
    1.07
     various
    1.05
    ضافة
    1.03
    Activations Density 0.008%

    No Known Activations