© 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. 34-GEMMASCOPE-RES-131K
    7. 30505
    Prev
    Next
    INDEX
    Explanations

    certified, license, generated, posted

    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
     beschäftigen
    -0.86
     became
    -0.85
     grew
    -0.82
    onChangeText
    -0.79
     тогда
    -0.79
     came
    -0.78
    pust
    -0.77
     quickly
    -0.77
    Litteratur
    -0.75
     metų
    -0.74
    POSITIVE LOGITS
     arisen
    0.92
    been
    0.90
    enty
    0.88
    ✵
    0.86
    bof
    0.86
     sejak
    0.83
     Spal
    0.83
    [:,
    0.83
    膨胀
    0.83
    SFD
    0.82
    Activations Density 0.059%

    No Known Activations