© 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. 5760
    Prev
    Next
    INDEX
    Explanations

    explaining what something is

    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
    ために
    1.24
     trazendo
    1.20
     músico
    1.16
     barco
    1.15
    サラ
    1.15
    卆
    1.15
     strumento
    1.15
    豕
    1.12
     Considerando
    1.12
    朿
    1.12
    POSITIVE LOGITS
     rằng
    1.42
    ว่า
    1.42
     how
    1.41
     bahwa
    1.33
     that
    1.25
     whether
    1.22
     why
    1.20
    ว่าจะ
    1.16
     what
    1.10
    how
    1.09
    Activations Density 0.164%

    No Known Activations