© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110548
    Prev
    Next
    INDEX
    Explanations

    calls for action, change, or cessation

    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_10/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
    いかがでしたか
    -1.42
     will
    -1.36
     one
    -1.35
     ['./
    -1.26
     condicionado
    -1.25
    ه‌ی
    -1.20
     inherently
    -1.18
     other
    -1.16
     profoundly
    -1.16
    ）-
    -1.15
    POSITIVE LOGITS
     to
    1.80
     لأنه
    1.30
     网
    1.18
     电子
    1.17
     summari
    1.12
    aknya
    1.09
    только
    1.08
    羶
    1.08
     mantis
    1.08
     by
    1.08
    Activations Density 0.095%

    No Known Activations