© 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. 25597
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    entikan
    -0.98
     jugu
    -0.96
    antom
    -0.95
    𝗘
    -0.95
     Bengaluru
    -0.93
    ૨
    -0.93
    arım
    -0.92
     tertentu
    -0.92
    anın
    -0.91
    nasional
    -0.91
    POSITIVE LOGITS
    计时
    1.02
    Auszeichnungen
    1.00
     vinculado
    0.96
     explic
    0.94
     Kiedy
    0.94
     veľa
    0.93
    Šalt
    0.93
     رہ
    0.93
    4
    0.91
     voľ
    0.91
    Activations Density 0.004%

    No Known Activations