© 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. 8259
    Prev
    Next
    INDEX
    Explanations

    North and South Dakota

    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
     With
    -2.45
    '
    -2.25
    他的
    -2.22
    畕
    -2.20
     bidra
    -2.19
    /"
    -2.17
    榈
    -2.13
    龱
    -2.09
    囹
    -2.05
    簠
    -2.05
    POSITIVE LOGITS
     notre
    2.69
    趼
    2.36
     we
    2.34
     be
    2.27
    怎么做
    2.22
    姈
    2.20
    Dakota
    2.19
    ai
    2.17
    ”—
    2.17
    塤
    2.13
    Activations Density 0.006%

    No Known Activations