© 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. 86697
    Prev
    Next
    INDEX
    Explanations

    actions, states, or outcomes

    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
    l
    -1.71
    The
    -1.48
     kurzem
    -1.40
    Namun
    -1.38
    fromUtf
    -1.38
    These
    -1.36
    つ
    -1.34
     Gründe
    -1.33
    ﹅
    -1.31
    𓐍
    -1.30
    POSITIVE LOGITS
    -
    2.00
     the
    1.52
     fertig
    1.47
    醫生
    1.41
     today
    1.41
    君は
    1.38
     here
    1.37
    ਞ
    1.35
     seem
    1.35
     separate
    1.32
    Activations Density 0.212%

    No Known Activations