© 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. 25674
    Prev
    Next
    INDEX
    Explanations

    Phantom Gourmet, package structure, Q:, Hi there, We usually

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

    The neuron is detecting timestamp‐style numeric patterns (e.g. colon‐separated time codes).

    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
     spesielt
    -1.09
     use
    -1.01
     an
    -0.97
    izarea
    -0.94
    wur
    -0.92
     with
    -0.90
     черная
    -0.89
    ङ
    -0.89
     stup
    -0.88
     Limoges
    -0.87
    POSITIVE LOGITS
    TacToe
    1.16
     setelan
    1.10
    沵
    1.06
     Tidak
    1.05
     Konkur
    1.04
    uleiro
    1.03
    libatkan
    1.00
     Официальный
    0.99
     reisen
    0.99
     cucharadita
    0.99
    Activations Density 0.001%

    No Known Activations