© 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. 89855
    Prev
    Next
    INDEX
    Explanations

    technical instructions and errors

    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
     ваз
    -1.30
    สามารถ
    -1.28
    Alright
    -1.24
    -1.19
     technological
    -1.18
    rač
    -1.18
    conjugated
    -1.15
     leitor
    -1.13
     aswell
    -1.12
     homepage
    -1.11
    POSITIVE LOGITS
     parms
    1.38
    𝒙
    1.34
     thru
    1.25
     someplace
    1.16
    Parms
    1.12
     Mga
    1.11
    IMHO
    1.10
    parms
    1.09
    クルマ
    1.09
     весьма
    1.09
    Activations Density 0.859%

    No Known Activations