© 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. 115905
    Prev
    Next
    INDEX
    Explanations

    centric, oriented, only

    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
    Bibliograf
    -0.84
    groupBy
    -0.78
    俱乐
    -0.77
    糅
    -0.77
     inspiri
    -0.76
    plings
    -0.76
    Składniki
    -0.75
    áver
    -0.74
     pagal
    -0.74
    𝒥
    -0.74
    POSITIVE LOGITS
     focused
    2.53
    focused
    2.34
     oriented
    2.31
     centric
    2.23
    oriented
    2.16
    only
    2.08
     dominated
    2.06
    centric
    2.02
     focussed
    1.99
     only
    1.86
    Activations Density 0.114%

    No Known Activations