© 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. 72060
    Prev
    Next
    INDEX
    Explanations

    place name followed by organization

    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
     verdura
    -1.10
     symboles
    -1.05
     Hanya
    -1.05
    驚く
    -1.04
     COMPOSITION
    -1.02
     Tienen
    -1.02
     setEmail
    -1.01
     aident
    -1.00
     ficaram
    -0.99
     comandante
    -0.99
    POSITIVE LOGITS
     It
    1.51
     it
    1.38
    ַּ
    1.20
    ּוֹ
    1.13
    ִּ
    1.13
    noStroke
    1.12
     its
    1.05
     Türkei
    1.04
    ၂
    1.03
    🥽
    1.03
    Activations Density 0.061%

    No Known Activations