© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12700
    Prev
    Next
    INDEX
    Explanations

    heartfelt thanks or goes out to

    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
    ج
    1.09
    𝐧
    0.99
    𝐪
    0.93
    نوع
    0.91
    𝐦
    0.91
    لو
    0.89
    ل
    0.86
     Cáceres
    0.84
    𝖎
    0.84
    ві
    0.84
    POSITIVE LOGITS
    1
    1.32
    2
    1.25
    4
    1.20
    8
    1.19
    3
    1.14
    5
    1.12
    9
    1.08
    st
    1.03
    ings
    1.02
    ours
    1.02
    Activations Density 0.001%

    No Known Activations