© 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. 30693
    Prev
    Next
    INDEX
    Explanations

    instructions installation setup

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

    The neuron strongly activates on standalone numeric tokens (e.g. version numbers or other multi‐digit numerals).

    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
    хам
    -0.91
    range
    -0.88
    >|</
    -0.86
     DOLLARS
    -0.84
    öhnen
    -0.84
     baden
    -0.83
     sqlSession
    -0.83
    ització
    -0.82
    fordable
    -0.82
    itys
    -0.82
    POSITIVE LOGITS
     erlauben
    0.84
     prerequisite
    0.84
     vorbere
    0.81
     gewohnt
    0.81
     umož
    0.78
     vyst
    0.78
     verpflich
    0.77
     divertido
    0.77
     letras
    0.76
     요청
    0.76
    Activations Density 0.001%

    No Known Activations