© 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. 36352
    Prev
    Next
    INDEX
    Explanations

    others or alternatives

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

    The neuron strongly fires on numeric tokens and list punctuation (e.g. colons, numbers, and decimal values), effectively spotting enumeration markers.

    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
     vano
    -1.08
     utiliser
    -1.07
     مشتر
    -1.02
     ژاپ
    -1.02
    tistic
    -1.00
     Tropfen
    -1.00
     zapatillas
    -0.97
     traduce
    -0.96
     souhait
    -0.96
     wykorzyst
    -0.94
    POSITIVE LOGITS
     other
    1.23
     others
    1.18
     anderen
    1.17
     or
    1.14
    为你
    1.13
    อื่น
    1.10
     also
    1.09
     you
    1.08
     lainnya
    1.03
    อีก
    1.02
    Activations Density 0.000%

    No Known Activations