© 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. 8793
    Prev
    Next
    INDEX
    Explanations

    currently experiencing

    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
     ++)
    0.57
     submission
    0.55
     arbitr
    0.55
     arbitrary
    0.55
     sha
    0.54
     boolean
    0.53
     .=
    0.52
    ."),
    0.51
    万里
    0.50
     kn
    0.49
    POSITIVE LOGITS
    elv
    0.57
    ätze
    0.56
    Flight
    0.54
     Rectangle
    0.54
    രെ
    0.54
     avantage
    0.53
     Ve
    0.53
     foes
    0.53
     Ч
    0.52
     Calculate
    0.52
    Activations Density 0.000%

    No Known Activations