© 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. 14542
    Prev
    Next
    INDEX
    Explanations

    advising or describing conditions

    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
     melts
    1.05
    et
    0.96
    sby
    0.95
    ו
    0.93
    ghe
    0.92
    t
    0.91
    ا
    0.91
    بے
    0.91
     подру
    0.89
    gling
    0.87
    POSITIVE LOGITS
    Submitted
    1.22
    ওয়ার্ড
    1.20
    ভাষায়
    1.20
     sonho
    1.19
    Sebelum
    1.19
    Antoine
    1.19
     această
    1.19
     conflicto
    1.19
    त्तीस
    1.18
    AllFilesIn
    1.17
    Activations Density 0.000%

    No Known Activations