© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 209
    Prev
    Next
    INDEX
    Explanations

    citation endings

    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
     beide
    -1.37
     черные
    -1.27
     kedua
    -1.27
     begge
    -1.26
     keduanya
    -1.19
     ambos
    -1.16
     filozof
    -1.14
    nuestro
    -1.14
     ។
    -1.13
    ælp
    -1.10
    POSITIVE LOGITS
     team
    1.11
     collectively
    1.09
     betreff
    1.07
     эффек
    1.06
     atualizar
    1.02
    广场
    1.00
     результа
    0.97
     similarly
    0.96
     reported
    0.95
    ;
    0.95
    Activations Density 0.006%

    No Known Activations