© 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. 3184
    Prev
    Next
    INDEX
    Explanations

    C++ include statements

    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
    pollution
    -0.85
    werty
    -0.84
     those
    -0.78
     only
    -0.78
     it
    -0.78
     хотя
    -0.76
     less
    -0.76
     although
    -0.73
     albeit
    -0.73
    俱
    -0.72
    POSITIVE LOGITS
     Whig
    0.90
    urts
    0.86
    doubt
    0.86
     [](
    0.86
    Doubt
    0.83
     EDUCATION
    0.80
     OAS
    0.80
     VFX
    0.77
    urt
    0.76
     doubtful
    0.76
    Activations Density 0.019%

    No Known Activations