© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130111
    Prev
    Next
    INDEX
    Explanations

    picked without replacement

    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
     anklicken
    -0.92
     inicialmente
    -0.89
    aian
    -0.88
    zmm
    -0.88
    tiara
    -0.86
     típicos
    -0.85
    éos
    -0.85
    uvu
    -0.83
     môžete
    -0.82
    щением
    -0.82
    POSITIVE LOGITS
    ၼ်း
    1.05
    vity
    0.94
    hnung
    0.92
    ⇨
    0.91
     fusca
    0.90
    ovich
    0.89
     varandra
    0.89
     запла
    0.89
    ルメ
    0.88
    imiento
    0.88
    Activations Density 0.016%

    No Known Activations