© 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. 42655
    Prev
    Next
    INDEX
    Explanations

    New, Latest, Generated

    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
    s
    -2.72
    ﾋ
    -2.09
    躄
    -2.02
    ی
    -1.96
    UGHTER
    -1.95
     队
    -1.95
     polícia
    -1.95
    荣
    -1.91
     prioriti
    -1.91
    のおかげ
    -1.88
    POSITIVE LOGITS
    ﮨ
    2.41
    ISSUE
    2.33
    ak
    2.30
     This
    2.23
    The
    2.22
    al
    2.17
    秾
    2.11
     奶油
    2.09
    las
    2.08
    If
    2.08
    Activations Density 0.009%

    No Known Activations