© 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. 4747
    Prev
    Next
    INDEX
    Explanations

    counting, cards, news, mechanism

    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
    ian
    0.93
    ية
    0.90
     स्पून
    0.86
    ℝ
    0.86
    ஓம்
    0.85
    abble
    0.82
    ＂
    0.82
    ᴙ
    0.82
    𝕚
    0.80
    byshev
    0.79
    POSITIVE LOGITS
    1.06
     một
    0.95
     în
    0.91
     vuoden
    0.89
     një
    0.88
     failings
    0.86
    రుగు
    0.82
    -}
    0.80
     unei
    0.80
     trong
    0.80
    Activations Density 0.778%

    No Known Activations