© 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. 15120
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and comments

    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
     its
    -1.26
    蓠
    -1.16
     GARANT
    -1.14
    TINGS
    -1.08
     évé
    -1.07
     bancaria
    -1.06
     Singers
    -1.05
     đình
    -1.05
     قابلیت
    -1.05
    ANTY
    -1.04
    POSITIVE LOGITS
     and
    1.74
     then
    1.33
     because
    1.27
     before
    1.23
     one
    1.21
    Then
    1.20
    Luego
    1.16
    いただいた
    1.15
     additional
    1.06
     マンション
    1.05
    Activations Density 0.000%

    No Known Activations