© 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. 142187
    Prev
    Next
    INDEX
    Explanations

    Adam occupied

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

    states of mind and control

    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
    acts
    0.46
     babel
    0.45
     verk
    0.45
     backups
    0.45
    ൻ
    0.45
    న్
    0.43
     dziecko
    0.43
    咾
    0.43
    Diameter
    0.43
     civilized
    0.43
    POSITIVE LOGITS
     concentrating
    0.50
    texttt
    0.46
    睨
    0.44
    分かり
    0.43
     წყ
    0.42
    ﻟ
    0.42
     আর্
    0.42
     развитие
    0.41
    間の
    0.40
    の使い方
    0.40
    Activations Density 0.001%

    No Known Activations