© 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. 34-GEMMASCOPE-RES-131K
    7. 64536
    Prev
    Next
    INDEX
    Explanations

    Naughty Strings

    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
    gbaar
    -0.83
    ovac
    -0.82
    ulosa
    -0.81
    claren
    -0.79
     banjir
    -0.79
    nargs
    -0.79
     mostrado
    -0.78
    xmlhttp
    -0.75
    chinen
    -0.75
     clás
    -0.74
    POSITIVE LOGITS
    disk
    0.84
     Epid
    0.80
     FACTORS
    0.78
    ring
    0.77
     sally
    0.76
     ring
    0.76
     Ring
    0.75
    RING
    0.73
     disqual
    0.71
     軽量
    0.71
    Activations Density 0.001%

    No Known Activations