© 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. 64122
    Prev
    Next
    INDEX
    Explanations

    method calls and syntax

    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
     goede
    -0.89
     Incredible
    -0.86
     Insight
    -0.82
    ఝ
    -0.82
     beoor
    -0.81
     jugado
    -0.81
     eenvou
    -0.80
     betere
    -0.78
     Muchos
    -0.77
    φαν
    -0.77
    POSITIVE LOGITS
    obj
    1.09
     x
    1.02
     obj
    0.94
    result
    0.90
     protagonista
    0.85
    args
    0.84
     result
    0.83
    被告
    0.83
     arr
    0.82
    您的
    0.78
    Activations Density 0.582%

    No Known Activations