© 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. 31-GEMMASCOPE-2-RES-262K
    7. 138940
    Prev
    Next
    INDEX
    Explanations

    suspension or suspended

    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
    剰
    0.52
     egalitarian
    0.50
     nationality
    0.49
     salaried
    0.46
     timeframe
    0.45
    diversity
    0.45
     idealistic
    0.45
     tireless
    0.44
    definite
    0.44
    vä
    0.43
    POSITIVE LOGITS
     Suspension
    0.55
     suspension
    0.51
     suspensions
    0.51
    悬
    0.51
     Would
    0.43
     susp
    0.43
    ”
    0.42
     suspended
    0.42
     controller
    0.41
     batteries
    0.41
    Activations Density 0.010%

    No Known Activations