© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12194
    Prev
    Next
    INDEX
    Explanations

    positive qualities describing outcomes

    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
     devenus
    -1.22
    -
    -1.21
    際に
    -1.20
     īpa
    -1.15
     semblent
    -1.15
     bewegen
    -1.09
     benötigen
    -1.08
    ניין
    -1.08
     découver
    -1.08
     vás
    -1.08
    POSITIVE LOGITS
    ebly
    1.28
     contributo
    1.09
     любом
    1.09
    <bos>
    1.07
     naves
    1.05
     クリック
    1.03
    砼
    1.02
     ammi
    1.01
     bloss
    0.99
     pcx
    0.99
    Activations Density 0.077%

    No Known Activations