© 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. 34-GEMMASCOPE-RES-131K
    7. 31393
    Prev
    Next
    INDEX
    Explanations

    technical term followed by specification

    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_34/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
     tunik
    -1.18
    Chris
    -1.14
    artigen
    -1.13
     bluz
    -1.12
     kamera
    -1.09
     มัน
    -1.06
     silikon
    -1.05
    ferien
    -1.05
     REALLY
    -1.05
    ké
    -1.05
    POSITIVE LOGITS
     wrongly
    1.30
     &
    1.27
     duly
    1.20
     upto
    1.16
     shortlisted
    1.10
     /
    1.08
     viz
    1.00
     trolley
    1.00
    osoever
    0.98
    шед
    0.97
    Activations Density 0.028%

    No Known Activations