© 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. 72922
    Prev
    Next
    INDEX
    Explanations

    state or change

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

    The main thing this neuron does is spot numeric statistics or counts.

    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
    )=>{
    -1.23
     profundas
    -1.16
    様に
    -1.09
    ≈
    -1.05
     profundos
    -1.02
     obtenir
    -1.02
     but
    -1.02
    Kr
    -1.02
     Наталья
    -1.01
    ≥
    -1.01
    POSITIVE LOGITS
     continues
    1.43
     is
    1.38
     continue
    1.34
     in
    1.33
     was
    1.28
     during
    1.27
    がありますが
    1.25
     has
    1.20
    peka
    1.20
    などを
    1.18
    Activations Density 0.105%

    No Known Activations