© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    programming and algorithms

    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
    arma
    1.04
    otal
    0.93
     προβ
    0.91
    ided
    0.89
     তখনই
    0.88
    잣
    0.88
    asadd
    0.87
     ১২শ
    0.87
    requent
    0.86
    servicetime
    0.85
    POSITIVE LOGITS
     déco
    1.11
     جناب
    1.07
     queridos
    1.06
     configuración
    1.05
     ژ
    1.05
     encontrar
    1.05
     Amplify
    1.04
     Gonna
    1.04
     ngại
    1.03
    袁
    1.03
    Activations Density 0.001%

    No Known Activations