© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8295
    Prev
    Next
    INDEX
    Explanations

    centuries and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_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
     hectares
    0.71
     dozen
    0.68
     thousand
    0.66
     ribu
    0.66
    thousand
    0.66
    씩
    0.65
     hundred
    0.64
     doses
    0.64
     shillings
    0.63
     stints
    0.63
    POSITIVE LOGITS
    ACT
    0.49
    master
    0.45
    authorization
    0.45
    Jill
    0.44
    check
    0.44
     നല്‍
    0.44
    search
    0.43
    system
    0.43
    Act
    0.42
    Z
    0.42
    Activations Density 0.117%

    No Known Activations