© 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. 33051
    Prev
    Next
    INDEX
    Explanations

    mathematical, code, or word problems

    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
    IFICACIÓN
    -1.02
     UIApplication
    -1.02
     pomys
    -1.01
     empuj
    -0.91
    ÍSTICAS
    -0.91
    templ
    -0.90
    жнарод
    -0.89
    ઋ
    -0.87
    膊
    -0.87
     pól
    -0.86
    POSITIVE LOGITS
    これも
    1.52
    こちらも
    1.24
     also
    1.15
     redefined
    1.13
     ebenfalls
    1.09
     также
    1.09
     Another
    1.07
    Another
    1.05
     is
    1.03
     их
    1.01
    Activations Density 0.042%

    No Known Activations