© 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. 2572
    Prev
    Next
    INDEX
    Explanations

    partial words and following context

    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
     adsor
    0.57
     adsorbent
    0.57
     functor
    0.57
     tranche
    0.57
     anisotrop
    0.57
    oubt
    0.56
     prerogative
    0.56
    ὖ
    0.56
     husbandry
    0.55
     ẞ
    0.55
    POSITIVE LOGITS
    Những
    0.65
     ktore
    0.57
    욌
    0.56
    萆
    0.55
    🍝
    0.54
     Những
    0.54
    🎸
    0.54
     외
    0.53
    🌋
    0.52
    䀠
    0.51
    Activations Density 0.280%

    No Known Activations