© 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. 34-GEMMASCOPE-RES-131K
    7. 2343
    Prev
    Next
    INDEX
    Explanations

    html form elements

    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
    褻
    -0.83
     ダイヤモンド
    -0.82
     salieron
    -0.76
    median
    -0.76
    }}">
    -0.75
    )}>
    -0.75
     sapphire
    -0.73
     sati
    -0.72
     Vortrag
    -0.72
    timedia
    -0.71
    POSITIVE LOGITS
     form
    2.00
    form
    1.65
     input
    1.32
     bentuk
    1.27
     forms
    1.25
     Form
    1.24
     формы
    1.10
     vorm
    1.07
     FORM
    1.05
    Form
    1.04
    Activations Density 0.007%

    No Known Activations