© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5901
    Prev
    Next
    INDEX
    Explanations

    The more information

    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
    นาะ
    1.71
    ців
    1.71
     jugadores
    1.67
    FromFile
    1.66
     culturales
    1.66
    挠
    1.65
     برگزاری
    1.65
    搧
    1.65
    icción
    1.65
     jugó
    1.63
    POSITIVE LOGITS
    ✬
    0.91
     Verified
    0.90
    ✮
    0.90
    ✦
    0.89
     clearest
    0.89
     fastest
    0.88
     Sain
    0.88
    ✓
    0.86
     easiest
    0.86
     ★
    0.86
    Activations Density 0.043%

    No Known Activations