© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 119022
    Prev
    Next
    INDEX
    Explanations

    English Edition AUDIOBOOK

    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
     surprisingly
    -1.04
     profoundly
    -1.01
     their
    -1.01
     postępo
    -0.98
     or
    -0.98
    気味
    -0.98
     touted
    -0.97
     moderately
    -0.96
     supremely
    -0.96
     wyłącznie
    -0.94
    POSITIVE LOGITS
    pecies
    1.15
    =()=>{
    1.05
    ;,
    0.99
    tili
    0.98
     spann
    0.97
     PROVIDE
    0.96
     ❤️
    0.96
    ']):
    0.95
    opies
    0.94
    FACTS
    0.91
    Activations Density 0.015%

    No Known Activations