© 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. 34123
    Prev
    Next
    INDEX
    Explanations

    html class and attributes

    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
     hinweg
    -0.98
    &
    -0.93
     nennen
    -0.92
     менее
    -0.91
    ded
    -0.90
     tarjo
    -0.89
    まぁ
    -0.88
     daarvoor
    -0.87
     sublime
    -0.86
    ulty
    -0.86
    POSITIVE LOGITS
     diamants
    1.10
     it
    1.07
     these
    1.02
    estos
    0.97
     they
    0.97
     we
    0.96
    ladı
    0.96
    belum
    0.92
    lede
    0.91
    satu
    0.90
    Activations Density 0.012%

    No Known Activations