© 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. 155222
    Prev
    Next
    INDEX
    Explanations

    roulette, license, injure

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

    sample, death, or still

    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
    ಗ್
    0.46
    珩
    0.45
    Enh
    0.44
    翊
    0.44
    厲
    0.44
    Aim
    0.43
    穷
    0.43
    긋
    0.43
    晏
    0.42
    гент
    0.42
    POSITIVE LOGITS
     historii
    0.49
     graces
    0.47
     continuare
    0.45
     observable
    0.45
     ().
    0.45
     realtà
    0.43
     nadal
    0.43
     ruj
    0.43
     paging
    0.42
    还是要
    0.42
    Activations Density 0.001%

    No Known Activations