© 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. 93382
    Prev
    Next
    INDEX
    Explanations

    event or number

    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
     providing
    -0.84
    Sila
    -0.78
     supplying
    -0.78
    Texte
    -0.75
    Detected
    -0.73
     helping
    -0.72
    nunca
    -0.71
    明らかに
    -0.71
    Methode
    -0.70
     provided
    -0.69
    POSITIVE LOGITS
    客户端
    0.85
    osas
    0.85
     voluntarios
    0.81
     accepté
    0.80
    لة
    0.80
    Sudan
    0.77
     печени
    0.77
     apparaît
    0.75
    latex
    0.75
     tanggal
    0.75
    Activations Density 0.028%

    No Known Activations