© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2152
    Prev
    Next
    INDEX
    Explanations

    code structure tokens

    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
    –)
    -1.37
     💕
    -1.20
     '!
    -1.18
     بداية
    -1.18
     semua
    -1.16
    )–
    -1.16
     '}
    -1.15
     стоко
    -1.13
     tujuh
    -1.13
     Ș
    -1.12
    POSITIVE LOGITS
     disregarding
    2.92
     definitively
    2.91
     hampered
    2.84
     relentlessly
    2.83
     convincingly
    2.83
     grossly
    2.80
     marginally
    2.78
     enlightening
    2.73
     hindering
    2.73
     delicately
    2.72
    Activations Density 8.803%

    No Known Activations