© 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. 13822
    Prev
    Next
    INDEX
    Explanations

    Spanish language and emotions

    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
     ContentView
    2.68
    Neigh
    2.30
    InstanceState
    2.24
    ke
    2.20
    べく
    2.11
    ւ
    2.08
    kron
    2.02
    kern
    1.99
    بوون
    1.99
    stehen
    1.98
    POSITIVE LOGITS
     dell
    2.67
     Chica
    2.46
    NewLabel
    2.41
    റാ
    2.35
    atı
    2.32
     terra
    2.29
    accharides
    2.24
    *}$
    2.22
    ierrez
    2.20
    atost
    2.19
    Activations Density 1.399%

    No Known Activations