© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10077
    Prev
    Next
    INDEX
    Explanations

    numerical identifiers and ranges

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

    numbers and currency

    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_40_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
     ocurren
    0.42
     ähnlich
    0.39
     semelh
    0.39
    雵
    0.38
     auff
    0.37
    ến
    0.37
    ámica
    0.37
    蜓
    0.36
     схо
    0.36
    ácie
    0.35
    POSITIVE LOGITS
     separatist
    0.47
     뭐가
    0.43
     tutt
    0.43
     doodles
    0.42
    htar
    0.42
     तबीयत
    0.41
     promov
    0.41
    particles
    0.40
     लिखें
    0.40
    TouchEvent
    0.40
    Activations Density 0.112%

    No Known Activations