© 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. 100529
    Prev
    Next
    INDEX
    Explanations

    pandas axis operations

    np_acts-logits-general · gemini-2.5-flash-lite

    pandas and programming-related parameter specifications or function arguments, particularly focusing on named parameters like 'header', 'axis', 'freq', 'periods', and 'prefix'.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     gesetzlichen
    -1.46
    zehnten
    -1.41
     лишь
    -1.40
     Ξ
    -1.40
    只会
    -1.39
     secretaria
    -1.38
     feststellen
    -1.38
     Aún
    -1.34
     ausdrück
    -1.33
     быть
    -1.32
    POSITIVE LOGITS
    </h2>
    1.45
     called
    1.34
     llamados
    1.25
     both
    1.24
    ？】
    1.20
     ५
    1.17
     global
    1.16
     about
    1.15
     an
    1.13
    教堂
    1.12
    Activations Density 0.008%

    No Known Activations