© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102819
    Prev
    Next
    INDEX
    Explanations

    open for business or public

    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
     bagay
    -0.88
     hyvä
    -0.87
     粥
    -0.82
    itiés
    -0.82
    öte
    -0.81
     buhay
    -0.80
    EMC
    -0.79
     kapag
    -0.79
    appearance
    -0.78
    ανε
    -0.77
    POSITIVE LOGITS
     anyone
    2.03
     everyone
    1.80
     everybody
    1.55
     anybody
    1.53
    Anyone
    1.35
    Everyone
    1.31
     всіх
    1.23
    anyone
    1.22
     all
    1.16
     public
    1.16
    Activations Density 0.032%

    No Known Activations