© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25196
    Prev
    Next
    INDEX
    Explanations

    single unique adjective phrase starts

    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_31_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
    ve
    0.48
    their
    0.46
    Overlay
    0.45
     разом
    0.43
     всех
    0.42
    当时
    0.42
    当时的
    0.42
    셨
    0.42
     toate
    0.41
    년
    0.41
    POSITIVE LOGITS
     orchards
    0.55
     armies
    0.46
     stockp
    0.46
     assays
    0.45
     showrooms
    0.44
     warehouses
    0.44
     lathes
    0.44
     trays
    0.43
     lattices
    0.43
     hypotheses
    0.43
    Activations Density 0.007%

    No Known Activations