© 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. 191502
    Prev
    Next
    INDEX
    Explanations

    Dutch independent bottler, royal designs, location

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

    US states, names, statuses

    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
    প্ত
    0.48
     alphanumeric
    0.46
    8
    0.46
    八
    0.44
    প্তি
    0.44
    三
    0.43
     gate
    0.42
    యాన్ని
    0.41
     agreements
    0.41
    门
    0.41
    POSITIVE LOGITS
    一款
    0.40
     কথাবার
    0.38
    Nice
    0.38
     Delay
    0.38
    Prove
    0.38
    Prol
    0.38
    Know
    0.37
     знаешь
    0.37
     Dispatch
    0.36
     அர்த்த
    0.36
    Activations Density 0.007%

    No Known Activations