© 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. 15568
    Prev
    Next
    INDEX
    Explanations

    Say Yes

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

    The neuron activates strongly on numeric characters or sequences (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
     from
    -1.56
     or
    -1.45
     their
    -1.16
     Australien
    -1.15
    Ū
    -1.05
    ctober
    -1.02
     bulan
    -1.02
     unusual
    -1.01
     веке
    -1.01
     would
    -1.00
    POSITIVE LOGITS
     eventually
    1.02
     praticamente
    1.01
     nivelul
    1.00
     incluso
    0.99
     Desired
    0.98
    关于
    0.96
     pyl
    0.96
     finalement
    0.96
     receiv
    0.96
    ÚBL
    0.95
    Activations Density 0.003%

    No Known Activations