© 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. 14981
    Prev
    Next
    INDEX
    Explanations

    content and documentation

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

    content creation, delivery, summarization

    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
     बड़ा
    0.53
    یک
    0.49
    ور
    0.45
    بد
    0.45
    斷
    0.44
    orphisms
    0.44
     informée
    0.43
    არ
    0.43
    ﻧ
    0.42
     بڑی
    0.42
    POSITIVE LOGITS
     content
    1.27
     Content
    1.27
     CONTENT
    1.16
     getContent
    1.15
     contenido
    1.13
    Content
    1.09
    content
    1.07
     内容
    1.07
     contents
    1.06
    CONTENT
    1.05
    Activations Density 0.041%

    No Known Activations