© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 6401
    Prev
    Next
    INDEX
    Explanations

    fairy lights, Vue.js, greenhouse gases, anime girl, bile duct, fiber, dimly lit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ная
    2.60
    ные
    2.56
    ную
    2.53
    acije
    2.43
    ной
    2.42
    емо
    2.39
    ing
    2.36
    ة
    2.36
    ิน
    2.33
    ь
    2.33
    POSITIVE LOGITS
    hovah
    1.47
    SearchCV
    1.47
     живело
    1.45
    깐
    1.39
    mael
    1.36
     relent
    1.34
    lect
    1.30
     RequestMethod
    1.28
     RegExp
    1.25
    indeer
    1.25
    Activations Density 0.428%

    No Known Activations