© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    speech and actions

    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
    getLogger
    -0.91
    posizione
    -0.90
    mma
    -0.85
     excitedly
    -0.82
     Nervous
    -0.81
     exclaim
    -0.81
    šta
    -0.80
    WillAppear
    -0.79
    Boys
    -0.79
    ֵ
    -0.79
    POSITIVE LOGITS
     mild
    0.87
     revived
    0.86
     festgelegt
    0.81
    是很
    0.81
     grim
    0.81
     misery
    0.80
     cristianismo
    0.79
    CARACTERIST
    0.78
     demolished
    0.77
    MODO
    0.76
    Activations Density 0.006%

    No Known Activations