© 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. 34-GEMMASCOPE-RES-131K
    7. 1475
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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_34/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
     জ
    -0.86
     originalmente
    -0.82
     actually
    -0.81
     rallado
    -0.77
     drenaje
    -0.77
     }^{\
    -0.75
    軋
    -0.75
     ampliamente
    -0.75
     даже
    -0.74
    期限
    -0.74
    POSITIVE LOGITS
    Baca
    0.87
    fahr
    0.82
    itados
    0.78
    購
    0.78
     erken
    0.78
    fuhr
    0.78
    Při
    0.78
    台灣
    0.78
     thrice
    0.77
     klok
    0.76
    Activations Density 0.051%

    No Known Activations