© 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. 38194
    Prev
    Next
    INDEX
    Explanations

    access, memory, testimony, yesterday

    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
    ן
    2.42
    ל
    2.08
    ০
    1.77
    க்கு
    1.54
    asjon
    1.54
    ujú
    1.51
    ça
    1.48
    ut
    1.45
    ów
    1.45
    ación
    1.41
    POSITIVE LOGITS
     ahuv
    1.73
    inafter
    1.72
    AppConstant
    1.69
    Tanggal
    1.68
    न
    1.68
    揄
    1.59
     ibang
    1.58
    ня
    1.57
    Harga
    1.54
    很多
    1.53
    Activations Density 0.000%

    No Known Activations