© 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. 118628
    Prev
    Next
    INDEX
    Explanations

    legal section or citation character

    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
    tamento
    -0.75
    SEGMENT
    -0.73
    mota
    -0.71
    MESSAGE
    -0.71
     alábbi
    -0.68
    =="")
    -0.68
    cey
    -0.68
     lumineuse
    -0.67
    加大
    -0.66
     SEQUENCE
    -0.66
    POSITIVE LOGITS
     §
    3.58
    §
    3.23
     (§
    2.64
     §§
    2.05
     §.
    1.71
     Sec
    1.64
     Sect
    1.61
     Section
    1.61
     $\$
    1.52
    Sec
    1.46
    Activations Density 0.043%

    No Known Activations