© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12214
    Prev
    Next
    INDEX
    Explanations

    sports and media references

    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
     for
    -1.27
     all
    -1.23
     my
    -1.20
     stycznia
    -1.19
    水墨
    -1.13
    歲
    -1.13
     skóry
    -1.08
     have
    -1.07
    大多
    -1.05
    :
    
    -1.05
    POSITIVE LOGITS
    Referensi
    1.30
     and
    1.27
    StoryboardSegue
    1.25
    ־ה
    1.20
     desactivar
    1.19
    踉
    1.18
    силання
    1.14
    וּ
    1.14
     familières
    1.13
    Recept
    1.13
    Activations Density 0.003%

    No Known Activations