© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58814
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers

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

    This neuron detects numeric tokens containing a decimal point (e.g. the decimal components in DOIs and other citation numbers).

    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
     and
    -2.48
     When
    -2.33
     commonly
    -2.30
     Despite
    -2.11
    );
    -2.11
    ’
    -2.08
     Although
    -1.98
     because
    -1.98
     designated
    -1.97
     During
    -1.94
    POSITIVE LOGITS
     of
    2.19
     trois
    2.06
     immense
    1.98
    helps
    1.96
    provides
    1.95
     insanely
    1.94
     USING
    1.94
    ícias
    1.91
     enorme
    1.90
     presque
    1.89
    Activations Density 0.004%

    No Known Activations