© 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. 14049
    Prev
    Next
    INDEX
    Explanations

    What is X?

    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
    ask
    0.79
    erees
    0.79
    向
    0.78
    getattr
    0.78
    rubyg
    0.77
     বহ
    0.76
    get
    0.76
    对
    0.76
    agre
    0.76
    zyloxy
    0.75
    POSITIVE LOGITS
     sementara
    1.32
    ᾗ
    1.22
     khusus
    1.13
     spesial
    1.09
     speciale
    1.09
    خص
    1.07
     lengkap
    1.06
    ֨
    1.06
    ϛ
    1.06
     ukon
    1.05
    Activations Density 0.113%

    No Known Activations