© 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. 890
    Prev
    Next
    INDEX
    Explanations

    restriction or cessation

    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
    色列
    3.08
    ي
    2.82
    м
    2.76
    কান্ত
    2.72
    ం
    2.63
    加坡
    2.59
    y
    2.58
    aient
    2.57
     SIINFEKL
    2.48
    ی
    2.46
    POSITIVE LOGITS
    痪
    2.21
    外部リンク
    2.07
    𝐬
    2.05
    𝚎
    2.01
    ten
    2.01
    ustan
    1.99
    ⿰
    1.99
    லாமல்
    1.98
    ump
    1.93
    𝚃
    1.92
    Activations Density 2.806%

    No Known Activations