© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112389
    Prev
    Next
    INDEX
    Explanations

    spouts, loops, subtitles, handle, logo, server

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

    technical product descriptions with compound noun phrases connected by "with".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     when
    -2.23
     there
    -1.81
     with
    -1.64
     reikia
    -1.55
     this
    -1.53
     because
    -1.48
     what
    -1.46
     while
    -1.44
     since
    -1.35
    今月
    -1.34
    POSITIVE LOGITS
    !!!!!!
    1.37
     zwischen
    1.32
     autre
    1.30
    痦
    1.30
     Each
    1.28
     Beide
    1.27
     Jeder
    1.26
     otras
    1.25
     pelig
    1.23
    !!!!!!!
    1.23
    Activations Density 0.377%

    No Known Activations