© 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. 34-GEMMASCOPE-RES-131K
    7. 25665
    Prev
    Next
    INDEX
    Explanations

    version 3.0 or 02:00

    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
    饺
    -0.78
     Atalanta
    -0.77
    ect
    -0.72
     Paseo
    -0.71
     bringe
    -0.69
     durante
    -0.69
    lir
    -0.69
     courriel
    -0.66
     Glamour
    -0.66
     possesses
    -0.66
    POSITIVE LOGITS
    charges
    0.84
    quered
    0.82
     signage
    0.79
    ところです
    0.77
    ابل
    0.77
    yntax
    0.77
    kres
    0.75
     overras
    0.75
    づらい
    0.75
    upuk
    0.74
    Activations Density 0.010%

    No Known Activations