© 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. 11406
    Prev
    Next
    INDEX
    Explanations

    stream / streamline

    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
    ੋਂ
    2.61
    tan
    2.44
    𝘦
    2.29
    men
    2.25
    mann
    2.09
    ton
    2.07
    ifndef
    2.02
    sworth
    2.02
    tay
    1.99
    𝘺
    1.99
    POSITIVE LOGITS
    ﺩ
    3.37
    ብስብ
    3.10
    ﻑ
    3.05
    ACKS
    2.96
    ﺙ
    2.95
     suaves
    2.88
    تدائي
    2.84
    ន្ថ
    2.81
    نیم
    2.76
    ﺱ
    2.76
    Activations Density 0.408%

    No Known Activations