© 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. 3706
    Prev
    Next
    INDEX
    Explanations

    demonstrable benefits

    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
    م
    1.54
    st
    1.40
    я
    1.36
    не
    1.29
    ين
    1.27
    ers
    1.23
    ін
    1.20
    쭉
    1.20
    м
    1.19
    ψη
    1.16
    POSITIVE LOGITS
    しかし
    1.38
    াম
    1.38
    ruppen
    1.33
    ਆ
    1.33
    এম
    1.28
    不過
    1.27
    ści
    1.23
    年に
    1.22
     الصوره
    1.22
     podendo
    1.21
    Activations Density 0.000%

    No Known Activations