© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7821
    Prev
    Next
    INDEX
    Explanations

    character, state, version, film, bacterium

    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
    féle
    1.20
    h
    1.01
    el
    0.95
    al
    0.93
    Jeśli
    0.92
    ında
    0.91
     Porém
    0.91
     Ancak
    0.89
     have
    0.86
    bė
    0.85
    POSITIVE LOGITS
     cisplatin
    1.06
     ReLU
    1.02
    的新
    0.97
     和
    0.96
     remod
    0.92
     renormal
    0.91
     cryptography
    0.89
     Hiroshima
    0.88
     AstraZeneca
    0.88
     cloro
    0.88
    Activations Density 0.141%

    No Known Activations