© 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. 310
    Prev
    Next
    INDEX
    Explanations

    vocabulary and alphabet

    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
    ع
    3.05
    ки
    2.86
    ка
    2.56
    ן
    2.56
    я
    2.48
    ע
    2.28
    ה
    2.19
    о
    2.11
    ა
    2.08
    мо
    2.05
    POSITIVE LOGITS
     thei
    1.86
    ᗩ
    1.80
     theseKeys
    1.71
    𝙳
    1.67
    般的
    1.66
     Huck
    1.66
    檛
    1.66
    ੍ਹ
    1.63
     Callie
    1.63
    prefixes
    1.60
    Activations Density 0.091%

    No Known Activations