© 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. 122546
    Prev
    Next
    INDEX
    Explanations

    rear door handles

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

    extreme conditions and creation

    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
    ﺗ
    0.54
    +"\
    0.54
     infinito
    0.52
    ﺙ
    0.52
    ﻓ
    0.49
     দুর্ঘটনা
    0.49
     উদ্ভাব
    0.49
    ﻘ
    0.49
    パ
    0.48
    infection
    0.48
    POSITIVE LOGITS
     hjel
    0.49
     annak
    0.49
     Bauer
    0.48
    ifizierung
    0.47
     Bak
    0.46
     Wal
    0.46
     seper
    0.46
     Sj
    0.46
     vaan
    0.45
    ched
    0.45
    Activations Density 0.000%

    No Known Activations