© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1841
    Prev
    Next
    INDEX
    Explanations

    weather forecast

    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_65k_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
     liệt
    1.52
    ich
    1.46
    另外
    1.46
    া
    1.45
    וב
    1.43
    터
    1.39
     referencing
    1.36
    kka
    1.35
    Kir
    1.35
    Walking
    1.35
    POSITIVE LOGITS
    ounsel
    1.52
     tain
    1.42
    raines
    1.32
    ายุ
    1.30
    ocrat
    1.29
     పాఠ
    1.29
     মাওলানা
    1.28
    ლებელია
    1.28
    getVideo
    1.28
    </em>
    1.28
    Activations Density 0.000%

    No Known Activations