© 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. 10-GEMMASCOPE-RES-131K
    7. 740
    Prev
    Next
    INDEX
    Explanations

    people and places

    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_10/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
    簠
    -2.98
    鼉
    -2.66
    蟶
    -2.45
    慙
    -2.41
    鱚
    -2.34
    魠
    -2.30
    킁
    -2.27
    饜
    -2.27
     значение
    -2.25
     avaient
    -2.23
    POSITIVE LOGITS
    ᚺ
    2.66
    t
    2.66
     für
    2.48
    鈊
    2.41
    }$,
    2.38
    to
    2.36
    1
    2.33
    Y
    2.31
    豨
    2.22
    il
    2.16
    Activations Density 0.003%

    No Known Activations