© 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. 5895
    Prev
    Next
    INDEX
    Explanations

    steal all, claim, threatened

    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
    惀
    0.56
    ரில்
    0.55
     pember
    0.54
     expectations
    0.54
     difficulties
    0.53
    困难
    0.52
     مشکلات
    0.52
     مشکل
    0.52
     ች
    0.52
     कृत
    0.52
    POSITIVE LOGITS
     coveted
    1.50
     claim
    1.48
     claiming
    1.44
    Claim
    1.37
     Claim
    1.34
    claim
    1.27
     claimed
    1.27
    搶
    1.23
     claims
    1.20
     monopol
    1.20
    Activations Density 0.326%

    No Known Activations