© 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. 16-GEMMASCOPE-2-RES-262K
    7. 31602
    Prev
    Next
    INDEX
    Explanations

    soak in the atmosphere

    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_16_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
     αφού
    0.61
     którym
    0.60
     אחרי
    0.57
     którego
    0.57
     contralateral
    0.57
    剋
    0.55
     котором
    0.55
     której
    0.55
    стые
    0.55
     sacchar
    0.54
    POSITIVE LOGITS
    o
    0.58
    /
    0.57
     frutos
    0.51
     the
    0.50
     lake
    0.50
     hanging
    0.50
     craftsmanship
    0.50
     HOA
    0.49
     “
    0.49
    ]
    0.49
    Activations Density 0.013%

    No Known Activations