© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1152
    Prev
    Next
    INDEX
    Explanations

    concepts and features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    大事
    1.64
     réforme
    1.59
    itul
    1.50
    佢
    1.48
    俱
    1.46
    tega
    1.39
    agues
    1.36
    spersed
    1.36
     anaemia
    1.35
    چنین
    1.35
    POSITIVE LOGITS
    8
    2.56
    7
    2.54
    zni
    2.40
    bies
    2.34
     ชั่วโมง
    2.34
    5
    2.30
    ٨
    2.28
     mesenchymal
    2.25
    6
    2.25
    3
    2.25
    Activations Density 0.051%

    No Known Activations