© 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. 109869
    Prev
    Next
    INDEX
    Explanations

    finding it [description]

    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
     verbinding
    -1.13
    感覺
    -1.10
     widać
    -1.01
     zacht
    -0.99
    nological
    -0.98
     natuurlijk
    -0.96
     vergeten
    -0.94
     edificios
    -0.94
    (/^
    -0.94
     biztos
    -0.93
    POSITIVE LOGITS
     to
    2.72
     useful
    1.30
     helpful
    1.29
     easier
    1.16
     appealing
    1.13
     irresistible
    1.13
     particularly
    1.10
     interesting
    1.10
     να
    1.10
     fascinating
    1.09
    Activations Density 0.023%

    No Known Activations