© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7993
    Prev
    Next
    INDEX
    Explanations

    talk about or elaborate on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ડી
    1.91
    typ
    1.88
    ה
    1.88
    候
    1.86
    generic
    1.85
    꺄
    1.85
     приема
    1.80
    showMessage
    1.78
     chắn
    1.76
    business
    1.75
    POSITIVE LOGITS
    ipede
    2.14
    िनल
    1.99
     اسماع
    1.96
    𝕖
    1.96
    یت
    1.94
     لات
    1.94
    ciata
    1.91
    льнай
    1.88
    viel
    1.82
    히려
    1.77
    Activations Density 0.119%

    No Known Activations