© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2312
    Prev
    Next
    INDEX
    Explanations

    let me know

    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
    ovol
    1.66
    opolitan
    1.56
    oretum
    1.50
    غراف
    1.46
    osph
    1.42
    𝚑
    1.41
    𝚎
    1.40
    1.38
    igraph
    1.37
    weets
    1.37
    POSITIVE LOGITS
    ン
    2.10
    тім
    1.74
     потря
    1.65
    a
    1.60
    る
    1.58
    マイ
    1.56
    のは
    1.54
    ে
    1.51
    に
    1.48
    ことは
    1.47
    Activations Density 0.153%

    No Known Activations