© 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. 34-GEMMASCOPE-RES-131K
    7. 33317
    Prev
    Next
    INDEX
    Explanations

    To introduce explanations or actions

    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
    ⾥
    -1.43
    выше
    -1.27
     asesinado
    -1.25
    りましたが
    -1.19
    sarung
    -1.16
    tifies
    -1.13
     victoires
    -1.12
    ϝ
    -1.10
     стоковые
    -1.09
    gebraucht
    -1.09
    POSITIVE LOGITS
     help
    2.13
     further
    2.00
     ensure
    1.97
     be
    1.84
     understand
    1.74
     avoid
    1.63
     better
    1.58
     know
    1.52
     learn
    1.52
     best
    1.52
    Activations Density 0.068%

    No Known Activations