© 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. 10-GEMMASCOPE-RES-131K
    7. 105871
    Prev
    Next
    INDEX
    Explanations

    would be followed by outcomes

    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_10/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
    h
    -2.25
    not
    -2.23
    1
    -2.17
    9
    -2.16
    it
    -2.09
    
    -2.08
    ꜆
    -2.08
    n
    -2.06
    ︕
    -1.98
    踭
    -1.96
    POSITIVE LOGITS
     Would
    2.70
    があれば
    2.09
    lossians
    2.05
     We
    2.02
     If
    1.98
    kve
    1.84
     evident
    1.78
     Was
    1.78
    。）
    1.77
     Option
    1.76
    Activations Density 0.021%

    No Known Activations