© 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. 109741
    Prev
    Next
    INDEX
    Explanations

    from Italy, referred pain, Air Force

    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
    ROWN
    0.62
     tł
    0.61
    atoti
    0.61
    𝓷
    0.59
     冖
    0.58
    WN
    0.57
    ઉન
    0.55
     ร
    0.55
     იყოს
    0.55
    ﻡ
    0.55
    POSITIVE LOGITS
    ъ
    0.61
    ly
    0.57
     eines
    0.55
    с
    0.55
    కు
    0.54
    ة
    0.54
    the
    0.53
    ко
    0.51
    ற்போது
    0.50
    Feb
    0.49
    Activations Density 0.000%

    No Known Activations