© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 60191
    Prev
    Next
    INDEX
    Explanations

    random number generation and modulo operations

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

    The neuron flags arithmetic operations (especially multiplication, division, etc.) in numeric expressions, such as those used in random‐number computations.

    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
    </blockquote>
    -1.84
     også
    -1.80
     גם
    -1.51
    Also
    -1.50
    It
    -1.50
    _
    -1.45
     puramente
    -1.37
    For
    -1.35
    doir
    -1.33
     auch
    -1.30
    POSITIVE LOGITS
     the
    2.31
     "}";
    1.43
    𞤢
    1.40
    𖣔
    1.40
    seamnă
    1.39
     }^{*}
    1.36
    _))
    1.35
     who
    1.35
    ሖ
    1.34
    zauber
    1.33
    Activations Density 0.001%

    No Known Activations