© 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. 186599
    Prev
    Next
    INDEX
    Explanations

    indicating or regarding

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

    users share conversations

    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
    tku
    0.52
    觛
    0.50
    
    0.47
    🈶
    0.47
    🚴
    0.46
    ﻷ
    0.46
    か月
    0.46
    同學
    0.45
     والأ
    0.45
    ্স
    0.44
    POSITIVE LOGITS
    indicate
    0.49
     concaten
    0.47
    is
    0.47
     Concerning
    0.47
     érz
    0.44
    regarding
    0.43
    Indic
    0.43
    gé
    0.43
    ge
    0.43
    accord
    0.42
    Activations Density 0.001%

    No Known Activations