© 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. 31452
    Prev
    Next
    INDEX
    Explanations

    Reserved or copyright notices

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

    The neuron fires on numeric tokens and numeric‐valued properties (e.g. version numbers, year dates, CSS parameter values).

    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
    ésia
    -0.71
     Ahmad
    -0.71
     Christine
    -0.70
    Element
    -0.69
     animal
    -0.69
    CSharp
    -0.68
     BD
    -0.68
     neste
    -0.67
    Ahmed
    -0.66
    atürk
    -0.66
    POSITIVE LOGITS
    ković
    0.70
     gefüllt
    0.66
    Benzene
    0.65
    remia
    0.65
    logna
    0.65
     sedation
    0.64
    ዩ
    0.64
     personnalité
    0.63
     keluar
    0.63
     nightfall
    0.63
    Activations Density 0.063%

    No Known Activations