© 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. 31003
    Prev
    Next
    INDEX
    Explanations

    "Attention is All You Need" paper

    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
    ี
    1.71
    iy
    1.59
    ع
    1.46
    ality
    1.45
     oblik
    1.38
    can
    1.31
    clusion
    1.27
    ॅमिली
    1.26
    مون
    1.25
    ikke
    1.25
    POSITIVE LOGITS
    ل
    1.27
    ENT
    1.22
    IES
    1.22
    ﮯ
    1.20
    tube
    1.20
    在
    1.20
    িন
    1.16
    CH
    1.16
    ล
    1.14
    ວກ
    1.12
    Activations Density 0.001%

    No Known Activations