© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4343
    Prev
    Next
    INDEX
    Explanations

    need, necessity, requirement

    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
    kita
    -0.91
     člove
    -0.89
    gesamt
    -0.85
     decisiones
    -0.84
     gewesen
    -0.82
    consola
    -0.82
     tervez
    -0.82
    farbe
    -0.80
    having
    -0.79
    rising
    -0.79
    POSITIVE LOGITS
     recourse
    1.30
     need
    1.30
     betrekking
    1.10
     access
    1.00
     conscience
    0.97
     nodig
    0.96
     Anspruch
    0.94
     дело
    0.94
    Need
    0.91
    need
    0.87
    Activations Density 0.022%

    No Known Activations