© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1314
    Prev
    Next
    INDEX
    Explanations

    Carolina, Lincoln, linear

    np_acts-logits-general · gemini-2.5-flash-lite

    linear equations and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.58
    
    0.52
    涞
    0.50
    tä
    0.48
    tamil
    0.48
    ɭ
    0.48
    funds
    0.46
    拉丁
    0.46
    lsulfanyl
    0.46
    𝗸
    0.46
    POSITIVE LOGITS
     linear
    1.05
     Linear
    0.94
     linearity
    0.92
     linearized
    0.90
     linearization
    0.88
     lineal
    0.85
     linéaire
    0.84
    linear
    0.84
     linearly
    0.84
     lin
    0.81
    Activations Density 0.035%

    No Known Activations