© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6873
    Prev
    Next
    INDEX
    Explanations

    practice, recordings, group, working, ask

    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
     outras
    0.65
    १८४
    0.64
     pastas
    0.61
     verkauft
    0.60
    앜
    0.60
     RNAs
    0.59
     curators
    0.59
    १८६
    0.59
     Wines
    0.58
     semaines
    0.57
    POSITIVE LOGITS
    面
    0.58
     群
    0.58
    visit
    0.57
    能
    0.57
     বা
    0.55
    デュ
    0.55
    ໃຊ້
    0.54
    传统
    0.54
    Collision
    0.53
    或
    0.53
    Activations Density 0.001%

    No Known Activations