© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104261
    Prev
    Next
    INDEX
    Explanations

    FRANK West

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

    The neuron strongly fires on isolated numeric tokens (e.g. years, page counts, standalone numbers) and otherwise stays off.

    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
     their
    -1.02
    Solubility
    -0.97
     its
    -0.91
    «<
    -0.90
    ουν
    -0.88
     lantaran
    -0.88
     susceptibles
    -0.88
     only
    -0.87
    }$;
    -0.87
     摄影
    -0.87
    POSITIVE LOGITS
     and
    1.05
    ériale
    1.02
    Postup
    1.01
    evt
    0.98
     finesse
    0.97
    br
    0.96
    RectF
    0.95
    adaş
    0.95
    politico
    0.92
    Câ
    0.90
    Activations Density 0.002%

    No Known Activations