© 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. 645
    Prev
    Next
    INDEX
    Explanations

    places and entities

    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
     ornamentation
    -1.55
    𝐽
    -1.48
    藹
    -1.45
    What
    -1.45
     }(\
    -1.42
    ovna
    -1.41
    💨
    -1.41
    geſ
    -1.41
    遄
    -1.40
    '>{
    -1.38
    POSITIVE LOGITS
     are
    2.08
    臯
    1.87
    僰
    1.75
    ."
    1.73
    ︲
    1.72
     但
    1.59
     same
    1.59
     have
    1.59
    苙
    1.58
    AT
    1.56
    Activations Density 0.032%

    No Known Activations