© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133792
    Prev
    Next
    INDEX
    Explanations

    external control or probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     erb
    0.41
     dimension
    0.41
     n
    0.38
    ্ি
    0.38
     hetero
    0.38
     compos
    0.38
     max
    0.37
    enity
    0.37
     urban
    0.37
    oxy
    0.37
    POSITIVE LOGITS
    Bitte
    0.45
    eggs
    0.44
    সুমে
    0.43
    SCOPE
    0.42
    Verse
    0.41
    Eggs
    0.41
    Within
    0.40
    棻
    0.40
    請
    0.40
    Please
    0.39
    Activations Density 0.000%

    No Known Activations