© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 103885
    Prev
    Next
    INDEX
    Explanations

    Vulkan

    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
    ()]
    0.45
    ]'
    0.44
    Program
    0.43
    Noise
    0.43
     honorable
    0.43
     erneut
    0.43
    .
    0.43
    ]
    0.42
    Mathematical
    0.42
     .
    0.41
    POSITIVE LOGITS
    óricos
    0.54
    গ
    0.50
     entidad
    0.47
    ipos
    0.47
    バ
    0.47
     LUM
    0.47
    aros
    0.47
     iluminación
    0.47
     В
    0.47
     bicicletas
    0.47
    Activations Density 0.000%

    No Known Activations