© 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. 115835
    Prev
    Next
    INDEX
    Explanations

    writing advice, specific items, and actions

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

    free plans and upgrades

    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
    נו
    0.33
     נ
    0.31
    პერ
    0.31
    п
    0.31
    а
    0.30
    נ
    0.30
    ﻣ
    0.30
    ἃ
    0.30
    м
    0.30
    ૨
    0.30
    POSITIVE LOGITS
     scavenging
    0.32
     önemlidir
    0.31
     cowork
    0.30
    是为了
    0.30
     MNIST
    0.30
     braucht
    0.29
     erit
    0.29
     داع
    0.29
     quieran
    0.29
    ခဲ့
    0.28
    Activations Density 0.116%

    No Known Activations