© 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. 34224
    Prev
    Next
    INDEX
    Explanations

    warnings and errors

    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
    اگر
    -1.13
    ⿺
    -1.09
     Policía
    -1.08
     Área
    -1.08
     Schwester
    -1.07
     também
    -1.06
    ]$.
    -1.05
     honte
    -1.05
     motocicleta
    -1.04
     Serviço
    -1.04
    POSITIVE LOGITS
    Zitat
    1.20
    いくつかの
    1.18
    Escrito
    1.17
    Hilsen
    1.16
    並沒有
    1.16
     மற்ற
    1.16
    参考にして
    1.15
    摒
    1.14
    それほど
    1.13
    Recept
    1.13
    Activations Density 0.006%

    No Known Activations