© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34625
    Prev
    Next
    INDEX
    Explanations

    burg or berg prefixes

    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
    躥
    -2.47
    ኧ
    -2.31
    🩻
    -2.30
     you
    -2.23
    的了
    -2.22
    焄
    -2.14
     dreamt
    -2.09
    Ᏻ
    -2.03
    x
    -2.02
    捽
    -1.98
    POSITIVE LOGITS
    </strong>
    2.56
     Because
    2.17
    糗
    2.08
     Each
    2.06
    煦
    2.05
    𝗴
    2.05
    $,
    2.03
     Zugang
    2.03
    。】
    2.02
     białe
    2.02
    Activations Density 0.017%

    No Known Activations