© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 12082
    Prev
    Next
    INDEX
    Explanations

    names followed by speech or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdio
    1.34
    蛳
    1.32
    နှစ်
    1.32
     কালিক
    1.30
    salad
    1.29
     supplic
    1.27
    ripción
    1.26
     eest
    1.26
     HStack
    1.25
    _{,
    1.22
    POSITIVE LOGITS
    as
    1.28
    kah
    1.23
    tet
    1.22
    ty
    1.22
    tere
    1.20
    subscribe
    1.18
     con
    1.17
    m
    1.16
    mari
    1.15
    are
    1.11
    Activations Density 0.002%

    No Known Activations