© 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. 109794
    Prev
    Next
    INDEX
    Explanations

    constructivist, constructive, design

    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
     cuticle
    -0.74
    ersoll
    -0.72
     București
    -0.69
    鷗
    -0.68
    ことができます
    -0.68
     dẫn
    -0.65
    さまでした
    -0.64
    Pol
    -0.64
    選舉
    -0.64
    Pag
    -0.63
    POSITIVE LOGITS
    StateList
    0.75
    츠
    0.72
     SSN
    0.72
     devo
    0.71
    maken
    0.66
    QPushButton
    0.65
    omel
    0.65
    edor
    0.65
     Accessed
    0.65
     CSM
    0.65
    Activations Density 0.086%

    No Known Activations