© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15066
    Prev
    Next
    INDEX
    Explanations

    harm/arm/herm/carm stems

    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
    atically
    0.64
    otions
    0.62
    shifts
    0.57
    primes
    0.54
    坞
    0.53
    嬤
    0.53
     vượt
    0.52
    meniz
    0.52
    persist
    0.52
    闪
    0.52
    POSITIVE LOGITS
     опера
    0.68
     arm
    0.63
     operator
    0.63
     herm
    0.63
    Operator
    0.63
    اس
    0.61
    ен
    0.59
     arms
    0.58
     Arm
    0.57
     অপারে
    0.57
    Activations Density 0.054%

    No Known Activations