© 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. 242135
    Prev
    Next
    INDEX
    Explanations

    on servers, own assessment, in data

    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
    。
    0.56
    in
    0.52
    Proven
    0.47
    
    0.45
     。
    0.44
     Daha
    0.43
    Ο
    0.43
     elapsed
    0.42
     accumulating
    0.42
    ;
    0.42
    POSITIVE LOGITS
    щаем
    0.47
    ዚህ
    0.46
    ṑ
    0.45
     средство
    0.43
     sogen
    0.41
    𝘶
    0.41
     이날
    0.41
    рованное
    0.41
    лого
    0.41
     وسلم
    0.41
    Activations Density 0.001%

    No Known Activations