© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2732
    Prev
    Next
    INDEX
    Explanations

    immediate danger or support

    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
    Negative Logits
    rı
    1.58
    കൊ
    1.40
    𝙧
    1.40
    rages
    1.38
     গড়ে
    1.37
     boasting
    1.37
    ან
    1.33
    𝚛
    1.32
    ㄹ
    1.31
    ╲
    1.31
    POSITIVE LOGITS
    이브
    1.51
    BB
    1.46
    Ap
    1.45
    ment
    1.43
    滓
    1.42
    Observable
    1.40
    সিডেন্ট
    1.36
    OKA
    1.35
    উন্ট
    1.33
     bột
    1.33
    Activations Density 0.097%

    No Known Activations