© 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. 65837
    Prev
    Next
    INDEX
    Explanations

    Q: or Bio:

    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
     botas
    -1.15
     camisas
    -1.10
     çanta
    -1.09
     éta
    -1.09
     lancé
    -1.08
     APPELL
    -1.08
     hilang
    -1.08
    Febru
    -1.08
     menik
    -1.07
     Diretto
    -1.05
    POSITIVE LOGITS
      
    1.02
     also
    0.98
    의
    0.93
    と
    0.93
     de
    0.92
    I
    0.91
    im
    0.91
    ere
    0.90
    rt
    0.90
     somewhat
    0.90
    Activations Density 0.001%

    No Known Activations