© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14593
    Prev
    Next
    INDEX
    Explanations

    learned to do something

    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
    ০০
    2.71
    ვე
    2.61
    েনারেল
    2.53
     živ
    2.33
    वाल
    2.30
    itism
    2.28
    糰
    2.28
    ോ
    2.26
     obr
    2.23
    வே
    2.18
    POSITIVE LOGITS
    chinen
    2.37
    ch
    2.36
    chodu
    2.19
    tı
    2.19
    าะ
    2.15
    ymoon
    2.11
     جبر
    2.08
     throwIf
    2.06
    TAIN
    2.01
    ták
    1.97
    Activations Density 0.078%

    No Known Activations