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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83366
    Prev
    Next
    INDEX
    Explanations

    celebrity news and analysis/predictions

    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
     invitaciones
    -0.77
    except
    -0.75
     lightweight
    -0.74
    EXPECTED
    -0.72
    skri
    -0.71
     hrd
    -0.71
     ザ
    -0.70
    关
    -0.70
     luxus
    -0.69
     cesse
    -0.69
    POSITIVE LOGITS
    tisserie
    0.73
    ADT
    0.73
     őket
    0.72
    enite
    0.69
     Chern
    0.69
     NBC
    0.69
    Игра
    0.68
     E
    0.68
    startX
    0.68
     satisf
    0.67
    Activations Density 0.006%

    No Known Activations