© 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. 33931
    Prev
    Next
    INDEX
    Explanations

    numeric characters and delimiters

    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
     years
    -1.31
     it
    -1.20
    ᾽
    -1.04
     It
    -1.03
    xFC
    -1.01
     its
    -0.99
    #%%
    -0.99
     \
    -0.98
     who
    -0.97
     ש
    -0.95
    POSITIVE LOGITS
    Елена
    1.24
     Guangdong
    0.98
    够了
    0.97
     exquis
    0.96
    Созда
    0.94
     subgoals
    0.93
     MEA
    0.93
     schreef
    0.92
    Бі
    0.91
     Hoi
    0.91
    Activations Density 0.010%

    No Known Activations