© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77275
    Prev
    Next
    INDEX
    Explanations

    company or enterprise details

    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
    arquía
    -0.88
     Grandma
    -0.83
     integran
    -0.82
    嵊
    -0.82
     grandma
    -0.81
    ciuto
    -0.80
    igor
    -0.79
     pela
    -0.79
     серьез
    -0.77
    lades
    -0.77
    POSITIVE LOGITS
     detail
    0.93
     Detail
    0.90
    detail
    0.86
     convention
    0.86
    person
    0.84
    Detail
    0.84
    ]<<"
    0.82
    Convention
    0.82
     Versions
    0.81
     жы
    0.81
    Activations Density 0.006%

    No Known Activations