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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49047
    Prev
    Next
    INDEX
    Explanations

    Code comments and structure

    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
     It
    -0.82
    $_,
    -0.81
     compagnia
    -0.81
    Statistics
    -0.80
    Frequency
    -0.79
     barva
    -0.79
     шири
    -0.79
     garbage
    -0.77
     discorso
    -0.77
     STATISTICS
    -0.77
    POSITIVE LOGITS
     molar
    1.11
     assumptions
    1.08
     assumed
    1.07
     dimensionless
    1.06
     thermodynamic
    1.02
     moist
    1.02
     enthalpy
    0.99
     assum
    0.99
    Fluent
    0.98
     humid
    0.96
    Activations Density 0.007%

    No Known Activations