© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118654
    Prev
    Next
    INDEX
    Explanations

    dwarf galaxies and spiral galaxies

    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
    riche
    -0.77
     duy
    -0.74
    axel
    -0.71
    estroyer
    -0.71
    ccin
    -0.69
    },[])
    -0.69
    DY
    -0.68
    czegó
    -0.68
    tı
    -0.66
     طالب
    -0.66
    POSITIVE LOGITS
     bulge
    1.12
     Gandalf
    0.91
     galaxies
    0.81
     elliptical
    0.80
     galaxy
    0.77
    ワシ
    0.75
    sians
    0.73
     Nana
    0.71
     Magnesium
    0.71
     Pact
    0.70
    Activations Density 0.029%

    No Known Activations