© 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. 22-GEMMASCOPE-RES-131K
    4. 73931
    Prev
    Next
    INDEX
    Explanations

    prefixes of words

    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_22/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
     Gehir
    -1.25
     ludzie
    -1.23
     Küste
    -1.20
     same
    -1.18
     célèbres
    -1.15
     Tamanho
    -1.12
     Acesso
    -1.10
    ְר
    -1.08
     why
    -1.08
     Entsche
    -1.07
    POSITIVE LOGITS
     heartfelt
    1.16
    rildi
    1.15
     neop
    1.14
    硕士
    1.14
     زیب
    1.13
     Prey
    1.12
    Viri
    1.11
     Filler
    1.11
     Surrogate
    1.08
    雏
    1.08
    Activations Density 0.012%

    No Known Activations