© 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. 5139
    Prev
    Next
    INDEX
    Explanations

    various languages and unrelated concepts

    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
    ิน
    0.90
    INDOW
    0.88
    itize
    0.87
    Humidity
    0.87
    listed
    0.86
    dex
    0.84
    habilit
    0.83
    6
    0.80
    ری
    0.79
    idenza
    0.79
    POSITIVE LOGITS
     wiele
    0.95
     einzelne
    0.89
    什么样的
    0.88
     hotly
    0.87
    খানে
    0.86
     carrots
    0.86
     greatness
    0.86
    这样的
    0.85
    зумі
    0.85
     quarrels
    0.83
    Activations Density 0.894%

    No Known Activations