© 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. 10-GEMMASCOPE-RES-131K
    7. 112739
    Prev
    Next
    INDEX
    Explanations

    to the

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

    The neuron detects numeric tokens (numbers expressed in 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_10/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
     first
    -2.33
     like
    -2.33
     with
    -2.23
     was
    -2.19
     worries
    -2.16
    ",
    -2.13
    '
    -2.09
    *
    -2.06
     difficult
    -2.02
    Like
    -1.97
    POSITIVE LOGITS
     the
    3.45
    皤
    2.63
     verhind
    2.50
    垟
    2.50
    锨
    2.27
     spécialiste
    2.22
    盉
    2.22
    烀
    2.13
     spezi
    2.13
    쨩
    2.11
    Activations Density 0.172%

    No Known Activations