© 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. 31915
    Prev
    Next
    INDEX
    Explanations

    outdated information or terms

    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
    };
    0.68
    ถ่าย
    0.62
    㗊
    0.61
    Dispatcher
    0.59
    㔹
    0.58
    懑
    0.57
    ีย
    0.57
     Cortana
    0.56
    Add
    0.56
    बाद
    0.56
    POSITIVE LOGITS
     outdated
    0.90
     archaic
    0.88
    y
    0.84
     antiquated
    0.80
    al
    0.78
    l
    0.77
     και
    0.74
     απο
    0.73
    u
    0.73
    z
    0.72
    Activations Density 0.007%

    No Known Activations