Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7502
    Prev
    Next
    INDEX
    Explanations

    NOT RECOMMENDED FOR FULL-TEXT PUBLICATION

    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
     while
    -1.09
     by
    -1.04
     policia
    -1.03
     lavish
    -1.02
     during
    -1.02
     truly
    -1.02
     their
    -1.01
     or
    -1.01
     despite
    -1.00
     extraordinary
    -0.98
    POSITIVE LOGITS
     alguns
    1.13
    Ô
    1.13
    Alright
    1.12
     bụ
    1.05
     Ii
    1.04
     услуг
    1.03
    ,;
    1.03
    }.
    1.03
    ggy
    1.02
     alcuni
    1.02
    Activations Density 0.001%

    No Known Activations