© 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. 5628
    Prev
    Next
    INDEX
    Explanations

    talking about concerns

    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
    hashTree
    1.44
     Diakses
    1.39
    ámara
    1.37
    arrêté
    1.37
    mán
    1.37
    roveň
    1.31
    Commenting
    1.30
    ặ
    1.29
    èlement
    1.29
    ayısıyla
    1.29
    POSITIVE LOGITS
     it
    1.59
     prove
    1.28
     as
    1.25
     we
    1.24
     quite
    1.22
     seem
    1.18
     type
    1.16
     logic
    1.15
     num
    1.12
     has
    1.12
    Activations Density 0.016%

    No Known Activations