© 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. 4357
    Prev
    Next
    INDEX
    Explanations

    Access Controlagency skillsresistant tosupply of

    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
    acariy
    0.42
    笾
    0.38
    änner
    0.36
    Parrocchia
    0.34
    ğinden
    0.34
    鳕
    0.34
    炁
    0.34
    गमेंट
    0.33
     początku
    0.33
    ittää
    0.33
    POSITIVE LOGITS
    <0x0D>
    0.43
    ↵
    0.39
                                   
    0.34
    0
    0.34
    </h2>
    0.33
    О
    0.32
    小
    0.31
       
    0.31
    0.31
         
    0.30
    Activations Density 0.000%

    No Known Activations