© 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. 43545
    Prev
    Next
    INDEX
    Explanations

    peace, universe, sugar, music, pressure

    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
     voici
    0.47
     Computing
    0.45
    nahi
    0.44
    妮
    0.44
     plaus
    0.42
     computing
    0.41
    蘚
    0.41
     თქვენ
    0.40
    ื้อง
    0.40
     NYU
    0.40
    POSITIVE LOGITS
    тя
    0.46
    pressure
    0.44
    buck
    0.40
    Grand
    0.40
    ¡
    0.39
     “
    0.39
    ─────
    0.39
    我现在
    0.39
    Total
    0.38
    ]-
    0.38
    Activations Density 0.011%

    No Known Activations