© 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. 3857
    Prev
    Next
    INDEX
    Explanations

    iodine and halides

    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
     hydroxy
    1.30
     admire
    1.29
     syphilis
    1.27
     antisense
    1.26
    ル
    1.26
    ษา
    1.24
     myosin
    1.24
     Estadual
    1.23
     antioxidants
    1.21
     ascor
    1.20
    POSITIVE LOGITS
    c
    1.68
    t
    1.55
    cape
    1.30
    cim
    1.27
    d
    1.25
    na
    1.24
    ne
    1.23
    cum
    1.23
    ishes
    1.23
    cale
    1.23
    Activations Density 0.001%

    No Known Activations