© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78241
    Prev
    Next
    INDEX
    Explanations

    numerical values and points

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

    The neuron strongly activates on standalone numeric tokens (digits and punctuation used in numbering), i.e. it detects numbers 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_34/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
    iable
    -0.87
     meditación
    -0.87
     adev
    -0.82
     and
    -0.77
     igra
    -0.76
    ーキ
    -0.75
    xique
    -0.75
     ngh
    -0.74
    FunctionFlags
    -0.74
    vaná
    -0.74
    POSITIVE LOGITS
     points
    1.43
     marks
    1.11
     pts
    1.07
    points
    1.04
    Points
    0.98
     begrenzt
    0.94
    Subtotal
    0.90
     allocated
    0.89
     überweisen
    0.84
    Pts
    0.84
    Activations Density 0.009%

    No Known Activations