© 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. 8224
    Prev
    Next
    INDEX
    Explanations

    Sarawak, Borneo, Sabah, Miri

    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
    萏
    -1.67
     bleus
    -1.59
     horloge
    -1.55
    1
    -1.52
    癭
    -1.51
    亊
    -1.45
    襌
    -1.41
     maillot
    -1.41
     ronde
    -1.40
     cópia
    -1.40
    POSITIVE LOGITS
    }$.
    2.03
     anything
    1.55
    StoryboardSegue
    1.55
    +}$
    1.52
    Solubility
    1.48
    *}$
    1.47
     Sarawak
    1.46
    uleiro
    1.46
    "])
    1.45
     as
    1.45
    Activations Density 0.009%

    No Known Activations