© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9318
    Prev
    Next
    INDEX
    Explanations

    develop and improve

    np_acts-logits-general · gemini-2.5-flash-lite

    actions and capabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    this
    0.38
    THIS
    0.38
    此
    0.38
    疑问
    0.36
     THIS
    0.36
    निम्
    0.34
    iphenyl
    0.34
    郗
    0.33
    你也
    0.33
    备注
    0.32
    POSITIVE LOGITS
     devel
    0.34
     make
    0.31
     develop
    0.31
     provide
    0.31
     re
    0.30
     streng
    0.30
     constantly
    0.30
     maximize
    0.29
     build
    0.29
     strengthen
    0.29
    Activations Density 0.350%

    No Known Activations