© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4485
    Prev
    Next
    INDEX
    Explanations

    Think of analogies

    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_24_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
    ї
    1.47
    у
    1.41
    и
    1.40
    cı
    1.38
    ми
    1.38
    cü
    1.27
    ке
    1.25
    ма
    1.22
    ką
    1.22
     وعلى
    1.21
    POSITIVE LOGITS
    G
    1.15
     granola
    1.14
     personnelle
    1.12
     vestib
    1.09
    id
    1.06
     jurid
    1.05
     diminu
    1.05
    නී
    1.05
     venom
    1.04
    screw
    1.03
    Activations Density 0.035%

    No Known Activations