© 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. 34-GEMMASCOPE-RES-131K
    7. 118808
    Prev
    Next
    INDEX
    Explanations

    going or good conditions

    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_34/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
     voelen
    -0.74
     dingen
    -0.74
     宝
    -0.74
     bedenken
    -0.71
     растений
    -0.71
     assolutamente
    -0.68
     Màu
    -0.68
     projektu
    -0.68
     montrant
    -0.68
     Arbitration
    -0.67
    POSITIVE LOGITS
     going
    4.75
    Going
    3.11
    going
    3.11
     Going
    2.88
     GOING
    2.50
    GOING
    2.34
     goin
    2.13
    ไป
    1.63
     gaan
    1.59
     goes
    1.37
    Activations Density 0.015%

    No Known Activations