© 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. 7154
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

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

    phrases following "it", "are", "with", "used", "can", "allowed", "a", "we"

    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
     pabbaj
    0.33
     konuda
    0.33
     arcane
    0.32
    噱
    0.32
    োজেন
    0.32
    জনকে
    0.32
     guilds
    0.32
     paltry
    0.31
    谈判
    0.31
     религиоз
    0.31
    POSITIVE LOGITS
     Tuttavia
    0.40
    ermost
    0.39
     Weitere
    0.38
     Mga
    0.38
    ​​
    0.36
    ：
    0.36
     第一
    0.36
     其
    0.35
    y
    0.35
    ​​​​
    0.35
    Activations Density 0.115%

    No Known Activations