© 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. 36119
    Prev
    Next
    INDEX
    Explanations

    backup and data protection

    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
     there
    -1.38
     pracy
    -1.25
     oil
    -1.22
    !\!\
    -1.21
    lateinit
    -1.18
     opening
    -1.16
     among
    -1.14
    riterion
    -1.13
    centerX
    -1.13
     chắn
    -1.12
    POSITIVE LOGITS
     your
    1.50
     ſi
    1.45
     sauvegarde
    1.31
    TokenNameDOT
    1.31
     matelas
    1.30
     CONCERT
    1.28
    𝒙
    1.27
     CONGRESS
    1.25
    ysty
    1.25
     eſ
    1.23
    Activations Density 0.062%

    No Known Activations