© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138736
    Prev
    Next
    INDEX
    Explanations

    health and wellness solutions

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

    figurative and descriptive words

    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
    였다
    0.62
    ма
    0.62
    ко
    0.60
    пи
    0.59
    רו
    0.59
    ло
    0.58
    된다
    0.58
    ७
    0.58
    п
    0.57
    ૯
    0.57
    POSITIVE LOGITS
     hoặc
    0.62
     bylaws
    0.54
     waivers
    0.54
     creatives
    0.53
     mods
    0.52
     trackers
    0.52
     self
    0.51
     decorations
    0.50
     alleviate
    0.50
     reagents
    0.50
    Activations Density 0.002%

    No Known Activations