© 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-262K
    7. 202937
    Prev
    Next
    INDEX
    Explanations

    True or false statements

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

    Question-answer pairs or statements about factual information, often requiring verification or evaluation of truth value, particularly in educational or assessment contexts.

    eleuther_acts_top20 · claude-4-5-sonnetTriggered by @jamesnaruto04
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     ماذا
    0.44
     appunto
    0.44
    FlightID
    0.43
     чого
    0.43
    什麼
    0.43
     чего
    0.42
    ጠር
    0.42
    loge
    0.42
    ését
    0.42
    怎样的
    0.41
    POSITIVE LOGITS
     puedo
    0.58
     można
    0.54
    可以使用
    0.53
     สามารถ
    0.52
    我可以
    0.51
    可以在
    0.49
    False
    0.47
    大多数
    0.47
     Moż
    0.47
     можно
    0.46
    Activations Density 0.042%

    No Known Activations