© 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. 72871
    Prev
    Next
    INDEX
    Explanations

    fellow group members

    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
     or
    -1.00
     manquante
    -0.98
     établie
    -0.96
     jezelf
    -0.96
     для
    -0.96
    ками
    -0.95
    ionado
    -0.91
     vile
    -0.91
    amkeit
    -0.90
    ernoo
    -0.90
    POSITIVE LOGITS
     fellow
    2.02
     colleagues
    1.98
     peers
    1.72
     teammates
    1.65
    fellow
    1.52
     classmates
    1.51
    Fellow
    1.48
     teammate
    1.41
     collega
    1.32
     colleague
    1.30
    Activations Density 0.015%

    No Known Activations