© 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. 10-GEMMASCOPE-RES-131K
    7. 105603
    Prev
    Next
    INDEX
    Explanations

    atomizing

    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_10/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
    This
    -3.02
    which
    -2.97
     These
    -2.64
     We
    -2.58
     ähnliche
    -2.30
     ältere
    -2.30
    就是
    -2.25
    ur
    -2.25
     Miß
    -2.22
     Thank
    -2.19
    POSITIVE LOGITS
    珢
    2.77
     we
    2.64
    翃
    2.63
    为了
    2.56
    ଝ
    2.48
    釤
    2.41
     exakt
    2.38
    romas
    2.36
     limitado
    2.36
    gencias
    2.36
    Activations Density 0.012%

    No Known Activations