© 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. 71189
    Prev
    Next
    INDEX
    Explanations

    define, let, or set

    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
     praticamente
    -1.10
     why
    -0.98
    思议
    -0.97
     précédents
    -0.96
    多么
    -0.93
     vorigen
    -0.92
     essendo
    -0.91
     evitando
    -0.90
     ウール
    -0.90
    lln
    -0.89
    POSITIVE LOGITS
    ：
    1.08
    جموعة
    1.05
     uden
    1.04
    nowrap
    1.03
     kwietnia
    1.00
    ，「
    0.98
     mengalir
    0.97
    maxlength
    0.96
     stycznia
    0.95
     Geraadpleegd
    0.95
    Activations Density 0.040%

    No Known Activations