© 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. 110420
    Prev
    Next
    INDEX
    Explanations

    under development

    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
     really
    -1.35
     certainly
    -1.32
     just
    -1.16
     surely
    -1.12
     terribly
    -1.09
     ļoti
    -1.08
     quite
    -1.08
     probably
    -1.07
     so
    -1.07
     recently
    -1.05
    POSITIVE LOGITS
    <sup>
    1.39
     itali
    1.16
    ${\
    1.13
    ̴
    1.06
    had
    1.02
     грамм
    1.01
     dien
    1.01
    ={()
    1.00
    ᾽
    1.00
    wed
    0.98
    Activations Density 0.001%

    No Known Activations