© 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. 27889
    Prev
    Next
    INDEX
    Explanations

    call me or you

    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
    但这
    -1.01
    HasBeenSet
    -1.00
     residente
    -0.99
    illères
    -0.97
    ={()
    -0.93
     spend
    -0.93
    hmig
    -0.92
     leaflet
    -0.92
     लोगों
    -0.91
    ykjav
    -0.91
    POSITIVE LOGITS
     their
    1.45
     adelantado
    1.10
     memanggil
    1.09
     ejemplares
    1.02
    ofed
    1.01
    ματα
    1.01
    panasonic
    0.99
     profundos
    0.99
     löst
    0.98
     altavoz
    0.98
    Activations Density 0.010%

    No Known Activations