© 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. 33477
    Prev
    Next
    INDEX
    Explanations

    word followed by specific next word

    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
     tých
    -1.07
    udges
    -1.02
     větší
    -1.00
    这一切
    -0.99
     grafica
    -0.99
     vinagre
    -0.98
     fiscales
    -0.97
     правительства
    -0.96
     feuer
    -0.94
    可愛
    -0.92
    POSITIVE LOGITS
     its
    1.18
    (!__
    1.05
     должны
    0.96
    ᵉ
    0.94
    ッチリ
    0.94
    വാ
    0.94
    🚕
    0.91
    ">//
    0.90
     brig
    0.89
    ,:)
    0.89
    Activations Density 0.060%

    No Known Activations