© 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. 10-GEMMASCOPE-RES-131K
    7. 58382
    Prev
    Next
    INDEX
    Explanations

    ionization

    np_acts-logits-general · gemini-2.5-flash-lite

    numerical values in mathematical sequences or equations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     or
    -1.91
     pintadas
    -1.90
     cordón
    -1.81
    Lịch
    -1.70
    Dữ
    -1.63
    كتشاف
    -1.62
     this
    -1.58
     decorados
    -1.57
     decoradas
    -1.54
    urangan
    -1.51
    POSITIVE LOGITS
     soluzione
    1.78
    จำนวน
    1.62
     enorme
    1.59
    馓
    1.59
     scelta
    1.53
     рисунки
    1.49
     namorado
    1.49
     アンド
    1.45
     compito
    1.45
     eccl
    1.44
    Activations Density 0.009%

    No Known Activations