© 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. 42178
    Prev
    Next
    INDEX
    Explanations

    suspension or suspicion

    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_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
     I
    0.54
     It
    0.53
    stä
    0.52
    شاه
    0.48
    zik
    0.48
    疆
    0.48
     Pred
    0.47
    鿁
    0.47
    ási
    0.47
    审计
    0.47
    POSITIVE LOGITS
     suspend
    1.10
     suspensions
    1.09
    susp
    1.08
     suspending
    1.06
     sosp
    1.05
     suspension
    1.04
     suspended
    1.04
     сус
    1.04
     susp
    1.02
    Susp
    1.02
    Activations Density 0.016%

    No Known Activations