© 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. 98571
    Prev
    Next
    INDEX
    Explanations

    Bassam al-

    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
    rvats
    -0.86
     DAVIS
    -0.84
    Bson
    -0.75
     Libri
    -0.74
    sium
    -0.74
     Hurst
    -0.73
    ASL
    -0.73
     maître
    -0.73
     وهذا
    -0.71
    一阵
    -0.70
    POSITIVE LOGITS
    Keep
    0.74
    Ukra
    0.73
    tably
    0.72
    表的
    0.71
    忽
    0.69
     inc
    0.69
     keep
    0.69
    𝓞
    0.68
     okaza
    0.68
     millones
    0.68
    Activations Density 0.055%

    No Known Activations