© 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-262K
    7. 11078
    Prev
    Next
    INDEX
    Explanations

    chemical compounds or salts

    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
    اً
    1.25
    utia
    1.18
    
    1.09
    स्ट
    1.05
    nutí
    1.05
    ução
    1.04
    iniai
    0.97
    ೩
    0.97
    ijk
    0.96
    ené
    0.96
    POSITIVE LOGITS
     salts
    1.29
     hydroxide
    1.29
    ET
    1.17
     hydrolysis
    1.15
     phosphates
    1.13
     bicarbonate
    1.09
     CuSO
    1.03
     secreted
    1.02
     hydrate
    1.01
     hydraz
    1.00
    Activations Density 0.065%

    No Known Activations