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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57776
    Prev
    Next
    INDEX
    Explanations

    metadata and technical snippets

    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
     slide
    -0.75
     kere
    -0.68
     glanced
    -0.65
    帽
    -0.65
    Slide
    -0.65
     captivity
    -0.63
    🎬
    -0.63
    fclose
    -0.62
     Whit
    -0.62
     Slide
    -0.62
    POSITIVE LOGITS
    Просто
    0.71
     unsupported
    0.70
    Кстати
    0.70
     LIM
    0.69
    不支持
    0.67
    Помо
    0.66
    盹
    0.66
     άν
    0.66
    Crítica
    0.66
    ILLE
    0.65
    Activations Density 0.069%

    No Known Activations