© 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. 111328
    Prev
    Next
    INDEX
    Explanations

    manipulating systems, variations

    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
    淙
    0.44
    FixedWidth
    0.44
    軐
    0.44
     वित्तीय
    0.42
    widths
    0.42
     direzione
    0.41
    itettura
    0.41
    咘
    0.40
    عبير
    0.39
     خدمة
    0.39
    POSITIVE LOGITS
     lift
    0.41
    py
    0.40
     ones
    0.39
     truly
    0.39
     kale
    0.39
     bouch
    0.38
    ັນ
    0.37
    lift
    0.37
     слы
    0.37
    ัน
    0.36
    Activations Density 0.000%

    No Known Activations