© 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. 2602
    Prev
    Next
    INDEX
    Explanations

    on [article/noun/adverb]

    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
     average
    -0.94
    Average
    -0.88
     why
    -0.85
    average
    -0.85
     bidra
    -0.84
    風景
    -0.83
    there
    -0.82
     response
    -0.82
     gateway
    -0.81
    ме
    -0.81
    POSITIVE LOGITS
    reaching
    1.15
     occasions
    0.91
     reaching
    0.88
     故
    0.79
     tutt
    0.77
    discus
    0.77
     spéc
    0.75
    cosp
    0.75
     chegar
    0.75
    CHK
    0.75
    Activations Density 0.036%

    No Known Activations