© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14207
    Prev
    Next
    INDEX
    Explanations

    C/C++ code pointers

    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
    }
    -1.09
     vener
    -1.06
    伙伴
    -1.06
     EW
    -1.05
     zerstört
    -1.04
     Как
    -1.02
    ién
    -1.00
    мл
    -1.00
     dissu
    -1.00
     Если
    -1.00
    POSITIVE LOGITS
     honte
    1.18
     their
    1.16
    ślę
    1.14
     lära
    1.09
    cego
    1.09
    voltage
    1.09
     of
    1.09
     maît
    1.08
     mariée
    1.08
    を担当
    1.05
    Activations Density 0.004%

    No Known Activations