© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 27257
    Prev
    Next
    INDEX
    Explanations

    demonstrate, show, explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nějak
    0.52
     тоже
    0.48
     довольно
    0.48
     oder
    0.45
     ziemlich
    0.43
     vrlo
    0.43
     albo
    0.42
    卻
    0.42
     però
    0.42
     suele
    0.42
    POSITIVE LOGITS
     использованием
    0.41
     রাখবে
    0.40
     Lever
    0.39
     proactively
    0.38
    要有
    0.38
     Objectives
    0.38
     Increased
    0.38
    MOUNTAINS
    0.38
    ことにより
    0.38
    Repe
    0.37
    Activations Density 0.068%

    No Known Activations