© 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. 10-GEMMASCOPE-RES-131K
    7. 73513
    Prev
    Next
    INDEX
    Explanations

    literacy and illiteracy

    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_10/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
     he
    -2.34
    翃
    -2.30
    他和
    -2.08
    з
    -2.08
    闥
    -2.03
    ৣ
    -1.98
    poptotic
    -1.97
    に入れて
    -1.96
    ítez
    -1.94
    嵎
    -1.91
    POSITIVE LOGITS
    0
    2.19
     這
    2.06
    一個
    2.03
    .
    1.96
    ⽼
    1.91
    C
    1.87
     That
    1.86
    *
    1.86
     那
    1.83
    ここは
    1.83
    Activations Density 0.005%

    No Known Activations