© 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. 12-GEMMASCOPE-2-RES-262K
    7. 30442
    Prev
    Next
    INDEX
    Explanations

    defines input fields

    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_12_width_262k_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
    ৮
    1.31
    yan
    1.23
    א
    1.23
    ל
    1.20
    castle
    1.07
    𝐈
    1.07
     해도
    1.06
    ९
    1.05
    fabrik
    1.05
    a
    1.05
    POSITIVE LOGITS
     heres
    0.99
    ికె
    0.97
    ين
    0.94
     correspon
    0.93
     cranks
    0.93
     diarr
    0.91
     deline
    0.91
     mixtape
    0.88
     lending
    0.87
     мате
    0.87
    Activations Density 0.001%

    No Known Activations