© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85065
    Prev
    Next
    INDEX
    Explanations

    the followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly responds to floating‐point numeric literals (numbers containing a decimal point) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     menghasilkan
    -1.46
     břez
    -1.46
     októ
    -1.46
    させて頂
    -1.44
     even
    -1.39
    ᎑
    -1.39
     schnelle
    -1.39
    χρι
    -1.39
    蕺
    -1.38
     asig
    -1.37
    POSITIVE LOGITS
    </strong>
    1.27
    }{
    1.25
    },
    1.25
     —
    1.23
    name
    1.21
    about
    1.20
     solches
    1.20
    )
    1.20
    });
    1.20
    |
    1.20
    Activations Density 0.060%

    No Known Activations