© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11807
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    𝑠
    2.84
    blow
    2.84
    ✶
    2.58
     ι
    2.56
    paths
    2.51
    bells
    2.50
    matt
    2.49
    א
    2.47
    𝐸
    2.44
    𝑖
    2.42
    POSITIVE LOGITS
    𝗻
    2.99
    𝗼
    2.92
    𝗲
    2.89
    𝘂
    2.87
    蔔
    2.76
    सायनिक
    2.75
    ůže
    2.75
    𝗱
    2.70
    𝗿
    2.64
    hus
    2.64
    Activations Density 0.001%

    No Known Activations