© 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. 105684
    Prev
    Next
    INDEX
    Explanations

    on track, in place, in suspension

    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
    kenal
    -1.63
    たまた
    -1.46
    內容簡介
    -1.43
    ﾔ
    -1.41
     mutta
    -1.38
    daging
    -1.38
    ﮑ
    -1.35
    nowy
    -1.34
    aruhi
    -1.33
     affiliations
    -1.31
    POSITIVE LOGITS
    set
    1.49
    self
    1.42
    al
    1.42
    0
    1.40
    他没有
    1.40
     isn
    1.39
    entiary
    1.38
    ay
    1.35
     somente
    1.35
     głównie
    1.34
    Activations Density 0.019%

    No Known Activations