© 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. 107034
    Prev
    Next
    INDEX
    Explanations

    software installation and removal

    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
    ónicos
    -0.88
    lara
    -0.87
    那
    -0.84
    )」
    -0.84
    edan
    -0.83
    ӓ
    -0.83
    loten
    -0.82
     compila
    -0.81
     Cbd
    -0.81
     Dawson
    -0.80
    POSITIVE LOGITS
    Namara
    0.88
     uninstall
    0.87
     зна
    0.85
    Programs
    0.85
     polluted
    0.81
     leftovers
    0.79
     removal
    0.79
     remove
    0.79
    limsy
    0.76
     espiritual
    0.73
    Activations Density 0.004%

    No Known Activations