© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98052
    Prev
    Next
    INDEX
    Explanations

    index files

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

    respond, assessment, monitoring, mood, compute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.60
    Material
    0.55
    Solo
    0.55
    偎
    0.51
    रासत
    0.49
    Lib
    0.49
    Harrison
    0.49
    .__
    0.49
    oer
    0.48
    Slice
    0.48
    POSITIVE LOGITS
     riduzione
    0.67
     feria
    0.63
     costit
    0.62
    фта
    0.60
     contaminación
    0.58
     увеличение
    0.57
     remover
    0.57
     crecimiento
    0.56
     ставак
    0.55
     facilidad
    0.54
    Activations Density 0.001%

    No Known Activations