© 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. 738
    Prev
    Next
    INDEX
    Explanations

    sensing things

    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
     Ironically
    -2.59
     When
    -2.47
     Shortly
    -2.45
     Extremely
    -2.31
     Currently
    -2.28
     jeweiligen
    -2.17
     Should
    -2.16
     Despite
    -2.09
     illustrious
    -2.08
     Virtually
    -2.08
    POSITIVE LOGITS
    衚
    2.69
    "]();
    2.19
    閦
    2.11
    蒾
    2.08
    ῞
    2.05
    ୬
    2.05
     ostavi
    2.03
    ,;
    2.02
    粜
    1.99
    赑
    1.98
    Activations Density 0.009%

    No Known Activations