© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4825
    Prev
    Next
    INDEX
    Explanations

    love story, greetings

    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_15_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
     indeks
    1.84
     spectrom
    1.77
    醗
    1.77
     terce
    1.77
     関数
    1.76
    subunit
    1.71
    contenido
    1.71
    オブジェクト
    1.66
    
    1.66
     estruturas
    1.64
    POSITIVE LOGITS
     أيضاً
    2.11
     منها
    1.97
    后续
    1.88
    在哪里
    1.84
     mith
    1.77
    鈎
    1.70
     كويس
    1.70
     إضافة
    1.70
     bhi
    1.69
    原来的
    1.65
    Activations Density 0.004%

    No Known Activations