© 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. 8940
    Prev
    Next
    INDEX
    Explanations

    so that.

    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
    5
    0.90
    4
    0.89
    1
    0.88
    3
    0.84
    2
    0.79
    ),
    0.74
     sucesso
    0.73
    8
    0.73
     condición
    0.71
    >,
    0.71
    POSITIVE LOGITS
    вая
    0.81
     ताकि
    0.77
     an
    0.73
    к
    0.72
     to
    0.69
     ώστε
    0.68
    以便
    0.67
    ків
    0.66
    尽快
    0.65
     it
    0.65
    Activations Density 0.054%

    No Known Activations