© 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. 31-GEMMASCOPE-2-RES-262K
    7. 12974
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, and totals

    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
     triangulation
    0.42
     headway
    0.41
     subtree
    0.40
     condemnation
    0.39
     triangles
    0.39
    </b>
    0.38
     meaning
    0.38
    ства
    0.38
     computation
    0.38
     miserably
    0.37
    POSITIVE LOGITS
     आरमारा
    0.45
    孅
    0.43
    θα
    0.43
    ണ്യ
    0.43
    liw
    0.42
    mitted
    0.42
     ආර
    0.42
     ″
    0.42
    मौसम
    0.41
     அறிமுக
    0.41
    Activations Density 0.000%

    No Known Activations