© 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. 12-GEMMASCOPE-2-RES-16K
    7. 8506
    Prev
    Next
    INDEX
    Explanations

    lead to negative outcomes

    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_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
    ं
    1.31
    ्या
    1.29
    lara
    1.27
    methoxy
    1.25
    Seit
    1.25
    屓
    1.23
    褴
    1.23
    ️⃣
    1.23
    rige
    1.22
    lardan
    1.21
    POSITIVE LOGITS
    о
    1.52
     talaga
    1.44
    у
    1.37
    ן
    1.37
     thường
    1.34
    finding
    1.33
     disasters
    1.30
    ED
    1.27
     Chưa
    1.27
     Abortion
    1.26
    Activations Density 0.027%

    No Known Activations