© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4073
    Prev
    Next
    INDEX
    Explanations

    ` =`, `):`, `,` after `img`, `msg`, `arr`

    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
    客様
    2.14
    ἆ
    2.02
    ето
    1.93
    uk
    1.84
    ae
    1.84
    ১
    1.77
    ha
    1.74
     Sono
    1.70
    とともに
    1.68
    yl
    1.67
    POSITIVE LOGITS
    علم
    2.11
    ع
    2.05
    ن
    2.03
    س
    1.80
    لای
    1.63
    न
    1.58
    лия
    1.54
    くちゃ
    1.53
    お客様
    1.51
    ről
    1.51
    Activations Density 0.503%

    No Known Activations