© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49147
    Prev
    Next
    INDEX
    Explanations

    starts with identifiers

    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
    componentWill
    -0.82
     AirPods
    -0.79
    这款
    -0.79
     vänt
    -0.77
     trữ
    -0.77
     gta
    -0.77
    寘
    -0.75
     Lulu
    -0.75
    阆
    -0.73
     стара
    -0.73
    POSITIVE LOGITS
    angered
    0.74
     coastline
    0.73
    agory
    0.73
     recent
    0.73
    茧
    0.71
    城市
    0.70
     künstler
    0.70
    โลก
    0.69
     beeindruck
    0.68
    Attn
    0.68
    Activations Density 0.009%

    No Known Activations