© 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. 11474
    Prev
    Next
    INDEX
    Explanations

    the followed by specific nouns

    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
    ρ
    2.00
     Sko
    1.96
     human
    1.87
    Г
    1.74
    shadow
    1.71
    lect
    1.69
    σ
    1.69
    Hb
    1.65
    yml
    1.62
    û
    1.61
    POSITIVE LOGITS
    ecek
    2.37
    تف
    2.37
    고
    2.21
    ので
    2.19
    ezi
    2.16
    eux
    2.12
    esinin
    2.12
    langan
    2.10
    תה
    2.08
    iapan
    2.08
    Activations Density 0.101%

    No Known Activations