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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8695
    Prev
    Next
    INDEX
    Explanations

    for women, physical, LGBTQ

    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
    c
    1.23
    ok
    1.12
    iv
    1.09
    pictured
    1.02
    k
    1.02
     RMSE
    0.98
     functors
    0.98
     annoy
    0.98
     acier
    0.98
     judgments
    0.96
    POSITIVE LOGITS
    ת
    1.37
    azione
    1.29
    ל
    1.28
    아
    1.27
    𝖆
    1.27
    다
    1.25
    له
    1.15
    ה
    1.13
    其
    1.11
    რ
    1.10
    Activations Density 0.273%

    No Known Activations