© 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. 30290
    Prev
    Next
    INDEX
    Explanations

    No followed by words

    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
    と
    -0.97
    Quién
    -0.95
     sientes
    -0.94
     допомогти
    -0.89
    jící
    -0.82
     puedas
    -0.81
    とろ
    -0.81
    沒有
    -0.81
     尔
    -0.81
     biraz
    -0.81
    POSITIVE LOGITS
     matter
    1.55
     longer
    1.44
    things
    1.23
     offense
    1.16
    inspection
    1.13
     way
    1.11
    tional
    1.11
    のイメージ
    1.10
    ためには
    1.07
    ised
    1.03
    Activations Density 0.095%

    No Known Activations