© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6402
    Prev
    Next
    INDEX
    Explanations

    disclaimers about not being a professional

    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
    *
    1.21
     rental
    1.20
     sprinkler
    1.15
    まったく
    1.13
    不住
    1.12
    hoc
    1.12
     Miramar
    1.12
    全く
    1.12
    =*
    1.11
    Oscar
    1.11
    POSITIVE LOGITS
     válto
    1.62
    пев
    1.50
     poesía
    1.45
     Victims
    1.41
    ॉल
    1.41
    伥
    1.36
    vagrant
    1.35
     attén
    1.33
    喟
    1.32
     víctimas
    1.31
    Activations Density 0.151%

    No Known Activations