© 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. 1255
    Prev
    Next
    INDEX
    Explanations

    copyright

    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
    を
    -0.87
     pitfalls
    -0.85
    などが
    -0.83
    шить
    -0.81
    んな
    -0.79
    子は
    -0.79
    株
    -0.77
    があり
    -0.77
    racks
    -0.75
    碁
    -0.75
    POSITIVE LOGITS
    émoc
    0.90
    ěj
    0.87
    pobla
    0.85
     gemeenten
    0.85
    ประ
    0.85
     بنات
    0.84
    تاریخ
    0.84
    墻
    0.82
     exitosa
    0.82
     vlees
    0.81
    Activations Density 0.002%

    No Known Activations