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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133768
    Prev
    Next
    INDEX
    Explanations

    ideology and discourse concepts

    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_40_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
    蹴
    0.40
    ardt
    0.39
    情報の
    0.39
     स्विच
    0.38
    蕎
    0.38
    工夫
    0.38
     منتقل
    0.38
     involuntary
    0.37
     suspended
    0.37
    貓
    0.37
    POSITIVE LOGITS
     multimodal
    0.52
     ideology
    0.46
    Disk
    0.45
     Disk
    0.45
     Ide
    0.44
     disk
    0.44
     ideologies
    0.44
     disc
    0.43
    disc
    0.40
     ide
    0.40
    Activations Density 0.018%

    No Known Activations