© 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
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1436
    Prev
    Next
    INDEX
    Explanations

    increase or difficulty

    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_7_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
    ا
    2.43
    gave
    2.20
    kannya
    2.15
    اا
    2.05
     ايا
    2.01
    an
    2.01
    te
    1.97
    se
    1.97
    rimer
    1.94
     Donner
    1.90
    POSITIVE LOGITS
     getWeather
    2.53
     agitation
    2.45
    场
    2.43
    }$\\
    2.39
    場
    2.38
    舴
    2.36
    >'
    2.36
     turbines
    2.36
    휋
    2.35
     activités
    2.35
    Activations Density 0.942%

    No Known Activations