© 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. 144039
    Prev
    Next
    INDEX
    Explanations

    negative mass-energy density

    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
    ških
    0.44
     spilling
    0.43
     тех
    0.42
     defunct
    0.42
     وأن
    0.41
     і
    0.41
    !“
    0.41
    ৷
    0.40
     и
    0.40
     ра
    0.40
    POSITIVE LOGITS
    s
    0.61
    g
    0.55
    gat
    0.53
     automatisch
    0.48
     instante
    0.48
     volat
    0.46
    saving
    0.45
    sustainable
    0.45
    ming
    0.44
    automat
    0.44
    Activations Density 0.001%

    No Known Activations