© 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. 138483
    Prev
    Next
    INDEX
    Explanations

    files, company, equip, raise, javelin

    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
     인해
    0.69
    让
    0.65
    హ
    0.63
     ఉండ
    0.63
     interchangeably
    0.63
    드
    0.63
    Cuenta
    0.61
    या
    0.61
    σό
    0.60
     přid
    0.59
    POSITIVE LOGITS
    و
    0.89
    ’
    0.77
    ande
    0.75
     y
    0.73
    '
    0.72
    ages
    0.66
    olver
    0.66
    '"
    0.66
     i
    0.65
    ic
    0.65
    Activations Density 0.000%

    No Known Activations