© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5452
    Prev
    Next
    INDEX
    Explanations

    introduces a reason

    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
     եւ
    1.44
    щаем
    1.28
    싸
    1.20
    ikulum
    1.20
    istos
    1.14
    utzerklärung
    1.08
    zantine
    1.07
     reunir
    1.07
    قى
    1.06
    adiyah
    1.05
    POSITIVE LOGITS
    #'
    2.56
     instability
    2.37
     affect
    2.36
     fluctuate
    2.33
     manejo
    2.29
    alanine
    2.28
     inactivity
    2.28
     Constraints
    2.27
    cephal
    2.27
     hinder
    2.27
    Activations Density 0.020%

    No Known Activations