© 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. 1636
    Prev
    Next
    INDEX
    Explanations

    Cost of Living, RAM, Model

    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
     biographer
    1.86
     is
    1.82
     historian
    1.75
     timeline
    1.63
     historians
    1.62
     timescale
    1.61
     was
    1.59
    鑊
    1.57
     Word
    1.55
    version
    1.54
    POSITIVE LOGITS
     nameless
    2.51
     десятки
    2.33
     nascent
    2.30
     những
    2.30
    那些
    2.29
     jednotliv
    2.26
    AndKeys
    2.25
     dozens
    2.25
    cada
    2.23
     unclaimed
    2.19
    Activations Density 0.521%

    No Known Activations