© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35930
    Prev
    Next
    INDEX
    Explanations

    framework components

    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
    édez
    -1.07
     to
    -0.98
    Crítica
    -0.93
     from
    -0.90
    맞
    -0.89
    <em>
    -0.88
    trische
    -0.85
    ᴏ
    -0.85
     palestra
    -0.84
    ียน
    -0.82
    POSITIVE LOGITS
    stö
    1.05
     οὐ
    1.05
    práv
    1.03
     guantes
    1.00
    outé
    0.96
     Turquie
    0.95
    работка
    0.94
     reservado
    0.94
     tatuajes
    0.93
    jścia
    0.93
    Activations Density 0.012%

    No Known Activations