© 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. 22-GEMMASCOPE-RES-131K
    7. 25412
    Prev
    Next
    INDEX
    Explanations

    rates per unit

    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
     both
    -0.99
     already
    -0.91
     paramInt
    -0.90
    笠
    -0.89
    既
    -0.88
     التالية
    -0.84
     getItemCount
    -0.83
    直到
    -0.81
    —
    -0.79
    ೫
    -0.79
    POSITIVE LOGITS
     per
    1.17
     என்ற
    1.15
    pared
    1.15
    espacio
    1.07
     voľ
    1.04
     gebruiken
    0.97
     voglia
    0.96
    notation
    0.96
    çeği
    0.94
    tienda
    0.94
    Activations Density 0.072%

    No Known Activations