© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118710
    Prev
    Next
    INDEX
    Explanations

    BC followed by identifiers

    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
     palatable
    -0.94
     Bari
    -0.83
     vielä
    -0.78
    Hasan
    -0.78
     granny
    -0.77
     princí
    -0.75
    hten
    -0.75
     Пред
    -0.74
    阵容
    -0.74
     crouch
    -0.73
    POSITIVE LOGITS
     BC
    1.27
    BC
    1.08
    bc
    1.05
     bc
    0.94
    bca
    0.88
    xbc
    0.84
    interface
    0.82
     stets
    0.82
     correct
    0.81
     Wissen
    0.81
    Activations Density 0.035%

    No Known Activations