© 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. 33247
    Prev
    Next
    INDEX
    Explanations

    money, questions, code, specific terms

    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
     this
    -1.24
    vaných
    -1.20
     ....
    -1.07
     .....
    -1.06
    　※
    -1.02
     добраться
    -0.99
     their
    -0.99
     déjà
    -0.98
     “...
    -0.98
    onPressed
    -0.98
    POSITIVE LOGITS
     is
    1.17
     čier
    1.13
    膣
    1.08
    chân
    1.07
     and
    1.05
    人格
    1.04
     pierwszej
    1.03
    german
    1.02
     egyéb
    1.02
     والف
    1.02
    Activations Density 0.003%

    No Known Activations