© 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. 4048
    Prev
    Next
    INDEX
    Explanations

    rise and elevation

    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
     downhill
    0.41
    бит
    0.40
    ח
    0.38
    ွက်
    0.38
    öffnet
    0.38
    ütter
    0.37
    δί
    0.37
    коменду
    0.37
     നി
    0.37
    ]-
    0.36
    POSITIVE LOGITS
     подня
    0.87
     поднима
    0.85
     вверх
    0.84
     yüks
    0.82
     rise
    0.81
     elevar
    0.80
     elevate
    0.76
     elevation
    0.75
     elevates
    0.74
     elevating
    0.74
    Activations Density 0.025%

    No Known Activations