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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109659
    Prev
    Next
    INDEX
    Explanations

    permutation and symmetric groups

    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_34/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
     SQU
    -0.78
     Undang
    -0.71
    Suppl
    -0.70
    wys
    -0.68
     Retrofit
    -0.68
    Cevapla
    -0.66
    CCR
    -0.66
    líben
    -0.65
    Gonz
    -0.65
    FF
    -0.65
    POSITIVE LOGITS
     permutation
    2.83
     permutations
    2.53
    Permutation
    2.33
    permutation
    2.30
     permu
    2.09
     perm
    2.02
    perm
    1.99
     Perm
    1.73
    Perm
    1.69
     swapping
    1.60
    Activations Density 0.064%

    No Known Activations