© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91255
    Prev
    Next
    INDEX
    Explanations

    components, markers, elements, Circular

    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_34/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
    ſi
    -0.84
     Официальный
    -0.81
    iqué
    -0.79
    嫗
    -0.78
    ął
    -0.77
    かなり
    -0.77
    ambilan
    -0.75
    ᅱ
    -0.74
     tempted
    -0.73
    demie
    -0.73
    POSITIVE LOGITS
     components
    0.96
    QC
    0.84
    dic
    0.80
    SAC
    0.76
    nders
    0.76
    loj
    0.74
     =
    0.74
    🟠
    0.72
    ite
    0.72
     Components
    0.72
    Activations Density 0.001%

    No Known Activations