© 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. 67434
    Prev
    Next
    INDEX
    Explanations

    programming imports, Memoirs

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     from
    -1.11
     to
    -1.10
    geç
    -1.09
     in
    -1.06
    hynch
    -1.04
    показа
    -1.00
    дени
    -0.97
    жал
    -0.96
     tapi
    -0.94
     лак
    -0.92
    POSITIVE LOGITS
     myriad
    1.12
     gebou
    1.05
     informiert
    1.03
     bekannten
    1.00
     pressione
    0.98
    geordnete
    0.98
     vorhandenen
    0.98
    continued
    0.97
     vorigen
    0.97
     blieben
    0.97
    Activations Density 0.001%

    No Known Activations