© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7634
    Prev
    Next
    INDEX
    Explanations

    explaining each step or part

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distributive
    1.03
     comfort
    1.03
     reproductive
    1.02
    ্বস্ত
    1.01
     conceivable
    1.01
     pipeline
    1.01
    倠
    1.01
    MDg
    1.00
     fairness
    0.99
     erotic
    0.99
    POSITIVE LOGITS
     Some
    0.81
     algumas
    0.81
     signé
    0.80
    は
    0.79
     operativo
    0.76
     feit
    0.76
    的操作
    0.74
    usuario
    0.73
     Tecnología
    0.71
     effectué
    0.70
    Activations Density 0.007%

    No Known Activations