© 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. 2661
    Prev
    Next
    INDEX
    Explanations

    hammered against

    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
    мулятор
    1.86
    Another
    1.82
    ulously
    1.81
    cyclohex
    1.81
    悵
    1.79
    ulator
    1.75
    бен
    1.68
    cyclopent
    1.68
    nity
    1.65
     '>'
    1.64
    POSITIVE LOGITS
     xét
    2.45
    भाषित
    2.31
     amenaza
    2.27
     etiquetas
    2.25
    唸
    2.19
     professores
    2.19
     tailles
    2.17
    ţiile
    2.17
     chaqueta
    2.16
     aparición
    2.14
    Activations Density 0.025%

    No Known Activations