© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7989
    Prev
    Next
    INDEX
    Explanations

    dies or death

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ﺪ
    1.05
    ﻴ
    0.95
     bravely
    0.92
     anionic
    0.88
     pokaz
    0.86
     destitute
    0.86
     diminuer
    0.86
    тся
    0.86
    ți
    0.85
     deputado
    0.84
    POSITIVE LOGITS
    ه
    1.19
    i
    1.09
    ી
    0.93
    inė
    0.89
    ąg
    0.86
    iate
    0.84
    k
    0.83
    "};
    0.80
    iene
    0.80
    iu
    0.77
    Activations Density 0.000%

    No Known Activations