© 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. 22-GEMMASCOPE-RES-131K
    7. 15521
    Prev
    Next
    INDEX
    Explanations

    news reported

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

    The neuron lights up on tokens that are part of named entities or numerical references (e.g. names, places, organizations, dates, and other digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     —
    -0.91
    <sup>
    -0.90
    fbe
    -0.89
     Your
    -0.84
    gfx
    -0.84
    äldrar
    -0.83
     κε
    -0.83
     cg
    -0.82
    jte
    -0.82
     apt
    -0.81
    POSITIVE LOGITS
     malang
    1.02
     then
    1.02
     lettore
    0.98
     PRINCIP
    0.94
     Betrach
    0.94
    weiterlesen
    0.93
     silenzio
    0.93
     Glaubens
    0.93
     quitt
    0.93
     domini
    0.91
    Activations Density 0.001%

    No Known Activations