© 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. 518
    Prev
    Next
    INDEX
    Explanations

    specify, set, or assign

    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
    wouldn
    -1.22
    similar
    -1.15
     และ
    -1.15
    hehehe
    -1.14
    wonderful
    -1.12
     botellas
    -1.10
    returning
    -1.10
     encont
    -1.09
    creating
    -1.09
    kinda
    -1.09
    POSITIVE LOGITS
     for
    2.16
     as
    1.45
     to
    1.38
     at
    1.34
     with
    1.20
     after
    1.20
     has
    1.16
     by
    1.15
     provides
    1.13
     makes
    1.10
    Activations Density 0.003%

    No Known Activations