© 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. 58772
    Prev
    Next
    INDEX
    Explanations

    outer rim

    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
    werke
    -0.84
    ALICE
    -0.74
     Roo
    -0.74
     BEC
    -0.73
     Gild
    -0.73
     ue
    -0.72
    лина
    -0.72
    ranje
    -0.71
     Cull
    -0.71
     Sherwood
    -0.71
    POSITIVE LOGITS
     flotation
    0.88
    rimp
    0.76
     Pfarrer
    0.75
    øv
    0.74
     Priester
    0.73
     chatting
    0.73
     Dual
    0.73
     Glä
    0.72
     hind
    0.72
     Everybody
    0.72
    Activations Density 0.027%

    No Known Activations