© 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. 128055
    Prev
    Next
    INDEX
    Explanations

    transferred to a recipient

    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
    横浜
    -1.30
     zapewnia
    -1.25
     gòn
    -1.22
     Majefty
    -1.21
     mascarilla
    -1.21
     việc
    -1.21
     使っ
    -1.20
     ficaram
    -1.20
    広島
    -1.19
     támogat
    -1.19
    POSITIVE LOGITS
     to
    5.63
     into
    2.77
     from
    1.55
     onto
    1.51
     out
    1.48
     back
    1.45
     towards
    1.39
     as
    1.38
     إلى
    1.30
     directly
    1.23
    Activations Density 0.052%

    No Known Activations