© 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. 110450
    Prev
    Next
    INDEX
    Explanations

    similar

    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
     stringBy
    -1.05
    zonych
    -1.05
    ่านั้น
    -1.04
     celta
    -1.00
    ⌂
    -0.98
    ragt
    -0.98
    次の
    -0.98
    ที่ยว
    -0.98
    siempre
    -0.97
    íze
    -0.96
    POSITIVE LOGITS
     similar
    7.97
    similar
    6.16
    Similar
    6.03
     Similar
    5.66
     podob
    5.31
     comparable
    4.94
    类似
    4.88
     ähnlich
    4.69
     similares
    4.59
     akin
    4.59
    Activations Density 0.492%

    No Known Activations