© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35165
    Prev
    Next
    INDEX
    Explanations

    binary choice

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

    The neuron activates on numeric tokens (sequences of digits or numeric 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_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
     THIRD
    -1.05
     and
    -1.05
    cended
    -1.05
    PasswordEncoder
    -1.05
    ???:
    -1.03
     such
    -1.02
    miert
    -1.02
    ån
    -1.01
    phalt
    -1.00
     TÉ
    -1.00
    POSITIVE LOGITS
     not
    1.10
     many
    1.08
     Many
    0.96
     nombreuses
    0.96
     innumerable
    0.94
     riemp
    0.90
    Szia
    0.90
    Descriere
    0.90
     significato
    0.89
     countless
    0.88
    Activations Density 0.039%

    No Known Activations