© 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. 104526
    Prev
    Next
    INDEX
    Explanations

    Combinatorial distribution Alfons

    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
     even
    -1.17
    LEBR
    -1.13
     lyder
    -1.11
    rückt
    -1.10
     pasaran
    -1.08
     persil
    -1.05
    SUNG
    -1.03
     kapas
    -1.02
     moreno
    -0.99
     Imperio
    -0.99
    POSITIVE LOGITS
    lexia
    1.02
    左側
    0.98
    amboo
    0.97
     reconocidos
    0.95
     considerazione
    0.94
     matchs
    0.93
    .;
    0.93
    agerie
    0.92
    那时候
    0.92
     freilich
    0.90
    Activations Density 0.001%

    No Known Activations