© 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. 34-GEMMASCOPE-RES-131K
    7. 117259
    Prev
    Next
    INDEX
    Explanations

    names starting with van

    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
     vera
    -0.87
     вашем
    -0.86
    Оп
    -0.86
    Informações
    -0.85
    Kenzie
    -0.85
    電子
    -0.83
    Procedimento
    -0.83
    Comentários
    -0.81
    Nunca
    -0.81
     Melhor
    -0.80
    POSITIVE LOGITS
     der
    1.09
    ches
    1.05
    ėse
    0.94
    ука
    0.89
    ânt
    0.89
    ⁡
    0.88
     den
    0.87
     passphrase
    0.85
     horen
    0.85
     passwords
    0.84
    Activations Density 0.007%

    No Known Activations