© 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. 14525
    Prev
    Next
    INDEX
    Explanations

    code placeholders like ${}

    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
     Strukt
    -1.34
     gekocht
    -1.32
     Krzysz
    -1.20
    iligen
    -1.16
     subió
    -1.15
     Projektu
    -1.12
     săptăm
    -1.12
    tempat
    -1.11
     Meksiko
    -1.09
     reizen
    -1.09
    POSITIVE LOGITS
     anyone
    1.16
     outcome
    1.12
     existing
    1.12
     patients
    1.09
     entire
    1.08
     reikia
    1.06
     ).
    1.05
    ないと
    1.03
     other
    1.02
     details
    1.02
    Activations Density 0.004%

    No Known Activations